Merge remote-tracking branch 'upstream/main' into vad_warnings

This commit is contained in:
makaveli10
2023-09-27 20:35:38 +08:00
26 changed files with 4158 additions and 39 deletions
View File
Binary file not shown.
Binary file not shown.
+4
View File
@@ -0,0 +1,4 @@
# Sphinx build info version 1
# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
config: 7b818b47e6f359b937e5a2517f120d43
tags: 645f666f9bcd5a90fca523b33c5a78b7
+26
View File
@@ -0,0 +1,26 @@
.. whisper_live documentation master file, created by
sphinx-quickstart on Fri Sep 22 11:39:30 2023.
You can adapt this file completely to your liking, but it should at least
contain the root `toctree` directive.
Welcome to Whisper Live documentation!
========================================
.. toctree::
:maxdepth: 2
.. automodule:: whisper_live.server
:members:
.. automodule:: whisper_live.client
:members:
Indices and tables
==================
* :ref:`genindex`
* :ref:`modindex`
* :ref:`search`
+703
View File
@@ -0,0 +1,703 @@
@import url("basic.css");
/* -- page layout ----------------------------------------------------------- */
body {
font-family: Georgia, serif;
font-size: 17px;
background-color: #fff;
color: #000;
margin: 0;
padding: 0;
}
div.document {
width: 940px;
margin: 30px auto 0 auto;
}
div.documentwrapper {
float: left;
width: 100%;
}
div.bodywrapper {
margin: 0 0 0 220px;
}
div.sphinxsidebar {
width: 220px;
font-size: 14px;
line-height: 1.5;
}
hr {
border: 1px solid #B1B4B6;
}
div.body {
background-color: #fff;
color: #3E4349;
padding: 0 30px 0 30px;
}
div.body > .section {
text-align: left;
}
div.footer {
width: 940px;
margin: 20px auto 30px auto;
font-size: 14px;
color: #888;
text-align: right;
}
div.footer a {
color: #888;
}
p.caption {
font-family: inherit;
font-size: inherit;
}
div.relations {
display: none;
}
div.sphinxsidebar a {
color: #444;
text-decoration: none;
border-bottom: 1px dotted #999;
}
div.sphinxsidebar a:hover {
border-bottom: 1px solid #999;
}
div.sphinxsidebarwrapper {
padding: 18px 10px;
}
div.sphinxsidebarwrapper p.logo {
padding: 0;
margin: -10px 0 0 0px;
text-align: center;
}
div.sphinxsidebarwrapper h1.logo {
margin-top: -10px;
text-align: center;
margin-bottom: 5px;
text-align: left;
}
div.sphinxsidebarwrapper h1.logo-name {
margin-top: 0px;
}
div.sphinxsidebarwrapper p.blurb {
margin-top: 0;
font-style: normal;
}
div.sphinxsidebar h3,
div.sphinxsidebar h4 {
font-family: Georgia, serif;
color: #444;
font-size: 24px;
font-weight: normal;
margin: 0 0 5px 0;
padding: 0;
}
div.sphinxsidebar h4 {
font-size: 20px;
}
div.sphinxsidebar h3 a {
color: #444;
}
div.sphinxsidebar p.logo a,
div.sphinxsidebar h3 a,
div.sphinxsidebar p.logo a:hover,
div.sphinxsidebar h3 a:hover {
border: none;
}
div.sphinxsidebar p {
color: #555;
margin: 10px 0;
}
div.sphinxsidebar ul {
margin: 10px 0;
padding: 0;
color: #000;
}
div.sphinxsidebar ul li.toctree-l1 > a {
font-size: 120%;
}
div.sphinxsidebar ul li.toctree-l2 > a {
font-size: 110%;
}
div.sphinxsidebar input {
border: 1px solid #CCC;
font-family: Georgia, serif;
font-size: 1em;
}
div.sphinxsidebar hr {
border: none;
height: 1px;
color: #AAA;
background: #AAA;
text-align: left;
margin-left: 0;
width: 50%;
}
div.sphinxsidebar .badge {
border-bottom: none;
}
div.sphinxsidebar .badge:hover {
border-bottom: none;
}
/* To address an issue with donation coming after search */
div.sphinxsidebar h3.donation {
margin-top: 10px;
}
/* -- body styles ----------------------------------------------------------- */
a {
color: #004B6B;
text-decoration: underline;
}
a:hover {
color: #6D4100;
text-decoration: underline;
}
div.body h1,
div.body h2,
div.body h3,
div.body h4,
div.body h5,
div.body h6 {
font-family: Georgia, serif;
font-weight: normal;
margin: 30px 0px 10px 0px;
padding: 0;
}
div.body h1 { margin-top: 0; padding-top: 0; font-size: 240%; }
div.body h2 { font-size: 180%; }
div.body h3 { font-size: 150%; }
div.body h4 { font-size: 130%; }
div.body h5 { font-size: 100%; }
div.body h6 { font-size: 100%; }
a.headerlink {
color: #DDD;
padding: 0 4px;
text-decoration: none;
}
a.headerlink:hover {
color: #444;
background: #EAEAEA;
}
div.body p, div.body dd, div.body li {
line-height: 1.4em;
}
div.admonition {
margin: 20px 0px;
padding: 10px 30px;
background-color: #EEE;
border: 1px solid #CCC;
}
div.admonition tt.xref, div.admonition code.xref, div.admonition a tt {
background-color: #FBFBFB;
border-bottom: 1px solid #fafafa;
}
div.admonition p.admonition-title {
font-family: Georgia, serif;
font-weight: normal;
font-size: 24px;
margin: 0 0 10px 0;
padding: 0;
line-height: 1;
}
div.admonition p.last {
margin-bottom: 0;
}
div.highlight {
background-color: #fff;
}
dt:target, .highlight {
background: #FAF3E8;
}
div.warning {
background-color: #FCC;
border: 1px solid #FAA;
}
div.danger {
background-color: #FCC;
border: 1px solid #FAA;
-moz-box-shadow: 2px 2px 4px #D52C2C;
-webkit-box-shadow: 2px 2px 4px #D52C2C;
box-shadow: 2px 2px 4px #D52C2C;
}
div.error {
background-color: #FCC;
border: 1px solid #FAA;
-moz-box-shadow: 2px 2px 4px #D52C2C;
-webkit-box-shadow: 2px 2px 4px #D52C2C;
box-shadow: 2px 2px 4px #D52C2C;
}
div.caution {
background-color: #FCC;
border: 1px solid #FAA;
}
div.attention {
background-color: #FCC;
border: 1px solid #FAA;
}
div.important {
background-color: #EEE;
border: 1px solid #CCC;
}
div.note {
background-color: #EEE;
border: 1px solid #CCC;
}
div.tip {
background-color: #EEE;
border: 1px solid #CCC;
}
div.hint {
background-color: #EEE;
border: 1px solid #CCC;
}
div.seealso {
background-color: #EEE;
border: 1px solid #CCC;
}
div.topic {
background-color: #EEE;
}
p.admonition-title {
display: inline;
}
p.admonition-title:after {
content: ":";
}
pre, tt, code {
font-family: 'Consolas', 'Menlo', 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', monospace;
font-size: 0.9em;
}
.hll {
background-color: #FFC;
margin: 0 -12px;
padding: 0 12px;
display: block;
}
img.screenshot {
}
tt.descname, tt.descclassname, code.descname, code.descclassname {
font-size: 0.95em;
}
tt.descname, code.descname {
padding-right: 0.08em;
}
img.screenshot {
-moz-box-shadow: 2px 2px 4px #EEE;
-webkit-box-shadow: 2px 2px 4px #EEE;
box-shadow: 2px 2px 4px #EEE;
}
table.docutils {
border: 1px solid #888;
-moz-box-shadow: 2px 2px 4px #EEE;
-webkit-box-shadow: 2px 2px 4px #EEE;
box-shadow: 2px 2px 4px #EEE;
}
table.docutils td, table.docutils th {
border: 1px solid #888;
padding: 0.25em 0.7em;
}
table.field-list, table.footnote {
border: none;
-moz-box-shadow: none;
-webkit-box-shadow: none;
box-shadow: none;
}
table.footnote {
margin: 15px 0;
width: 100%;
border: 1px solid #EEE;
background: #FDFDFD;
font-size: 0.9em;
}
table.footnote + table.footnote {
margin-top: -15px;
border-top: none;
}
table.field-list th {
padding: 0 0.8em 0 0;
}
table.field-list td {
padding: 0;
}
table.field-list p {
margin-bottom: 0.8em;
}
/* Cloned from
* https://github.com/sphinx-doc/sphinx/commit/ef60dbfce09286b20b7385333d63a60321784e68
*/
.field-name {
-moz-hyphens: manual;
-ms-hyphens: manual;
-webkit-hyphens: manual;
hyphens: manual;
}
table.footnote td.label {
width: .1px;
padding: 0.3em 0 0.3em 0.5em;
}
table.footnote td {
padding: 0.3em 0.5em;
}
dl {
margin-left: 0;
margin-right: 0;
margin-top: 0;
padding: 0;
}
dl dd {
margin-left: 30px;
}
blockquote {
margin: 0 0 0 30px;
padding: 0;
}
ul, ol {
/* Matches the 30px from the narrow-screen "li > ul" selector below */
margin: 10px 0 10px 30px;
padding: 0;
}
pre {
background: #EEE;
padding: 7px 30px;
margin: 15px 0px;
line-height: 1.3em;
}
div.viewcode-block:target {
background: #ffd;
}
dl pre, blockquote pre, li pre {
margin-left: 0;
padding-left: 30px;
}
tt, code {
background-color: #ecf0f3;
color: #222;
/* padding: 1px 2px; */
}
tt.xref, code.xref, a tt {
background-color: #FBFBFB;
border-bottom: 1px solid #fff;
}
a.reference {
text-decoration: none;
border-bottom: 1px dotted #004B6B;
}
/* Don't put an underline on images */
a.image-reference, a.image-reference:hover {
border-bottom: none;
}
a.reference:hover {
border-bottom: 1px solid #6D4100;
}
a.footnote-reference {
text-decoration: none;
font-size: 0.7em;
vertical-align: top;
border-bottom: 1px dotted #004B6B;
}
a.footnote-reference:hover {
border-bottom: 1px solid #6D4100;
}
a:hover tt, a:hover code {
background: #EEE;
}
@media screen and (max-width: 870px) {
div.sphinxsidebar {
display: none;
}
div.document {
width: 100%;
}
div.documentwrapper {
margin-left: 0;
margin-top: 0;
margin-right: 0;
margin-bottom: 0;
}
div.bodywrapper {
margin-top: 0;
margin-right: 0;
margin-bottom: 0;
margin-left: 0;
}
ul {
margin-left: 0;
}
li > ul {
/* Matches the 30px from the "ul, ol" selector above */
margin-left: 30px;
}
.document {
width: auto;
}
.footer {
width: auto;
}
.bodywrapper {
margin: 0;
}
.footer {
width: auto;
}
.github {
display: none;
}
}
@media screen and (max-width: 875px) {
body {
margin: 0;
padding: 20px 30px;
}
div.documentwrapper {
float: none;
background: #fff;
}
div.sphinxsidebar {
display: block;
float: none;
width: 102.5%;
margin: 50px -30px -20px -30px;
padding: 10px 20px;
background: #333;
color: #FFF;
}
div.sphinxsidebar h3, div.sphinxsidebar h4, div.sphinxsidebar p,
div.sphinxsidebar h3 a {
color: #fff;
}
div.sphinxsidebar a {
color: #AAA;
}
div.sphinxsidebar p.logo {
display: none;
}
div.document {
width: 100%;
margin: 0;
}
div.footer {
display: none;
}
div.bodywrapper {
margin: 0;
}
div.body {
min-height: 0;
padding: 0;
}
.rtd_doc_footer {
display: none;
}
.document {
width: auto;
}
.footer {
width: auto;
}
.footer {
width: auto;
}
.github {
display: none;
}
}
/* misc. */
.revsys-inline {
display: none!important;
}
/* Make nested-list/multi-paragraph items look better in Releases changelog
* pages. Without this, docutils' magical list fuckery causes inconsistent
* formatting between different release sub-lists.
*/
div#changelog > div.section > ul > li > p:only-child {
margin-bottom: 0;
}
/* Hide fugly table cell borders in ..bibliography:: directive output */
table.docutils.citation, table.docutils.citation td, table.docutils.citation th {
border: none;
/* Below needed in some edge cases; if not applied, bottom shadows appear */
-moz-box-shadow: none;
-webkit-box-shadow: none;
box-shadow: none;
}
/* relbar */
.related {
line-height: 30px;
width: 100%;
font-size: 0.9rem;
}
.related.top {
border-bottom: 1px solid #EEE;
margin-bottom: 20px;
}
.related.bottom {
border-top: 1px solid #EEE;
}
.related ul {
padding: 0;
margin: 0;
list-style: none;
}
.related li {
display: inline;
}
nav#rellinks {
float: right;
}
nav#rellinks li+li:before {
content: "|";
}
nav#breadcrumbs li+li:before {
content: "\00BB";
}
/* Hide certain items when printing */
@media print {
div.related {
display: none;
}
}
+925
View File
@@ -0,0 +1,925 @@
/*
* basic.css
* ~~~~~~~~~
*
* Sphinx stylesheet -- basic theme.
*
* :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
* :license: BSD, see LICENSE for details.
*
*/
/* -- main layout ----------------------------------------------------------- */
div.clearer {
clear: both;
}
div.section::after {
display: block;
content: '';
clear: left;
}
/* -- relbar ---------------------------------------------------------------- */
div.related {
width: 100%;
font-size: 90%;
}
div.related h3 {
display: none;
}
div.related ul {
margin: 0;
padding: 0 0 0 10px;
list-style: none;
}
div.related li {
display: inline;
}
div.related li.right {
float: right;
margin-right: 5px;
}
/* -- sidebar --------------------------------------------------------------- */
div.sphinxsidebarwrapper {
padding: 10px 5px 0 10px;
}
div.sphinxsidebar {
float: left;
width: 230px;
margin-left: -100%;
font-size: 90%;
word-wrap: break-word;
overflow-wrap : break-word;
}
div.sphinxsidebar ul {
list-style: none;
}
div.sphinxsidebar ul ul,
div.sphinxsidebar ul.want-points {
margin-left: 20px;
list-style: square;
}
div.sphinxsidebar ul ul {
margin-top: 0;
margin-bottom: 0;
}
div.sphinxsidebar form {
margin-top: 10px;
}
div.sphinxsidebar input {
border: 1px solid #98dbcc;
font-family: sans-serif;
font-size: 1em;
}
div.sphinxsidebar #searchbox form.search {
overflow: hidden;
}
div.sphinxsidebar #searchbox input[type="text"] {
float: left;
width: 80%;
padding: 0.25em;
box-sizing: border-box;
}
div.sphinxsidebar #searchbox input[type="submit"] {
float: left;
width: 20%;
border-left: none;
padding: 0.25em;
box-sizing: border-box;
}
img {
border: 0;
max-width: 100%;
}
/* -- search page ----------------------------------------------------------- */
ul.search {
margin: 10px 0 0 20px;
padding: 0;
}
ul.search li {
padding: 5px 0 5px 20px;
background-image: url(file.png);
background-repeat: no-repeat;
background-position: 0 7px;
}
ul.search li a {
font-weight: bold;
}
ul.search li p.context {
color: #888;
margin: 2px 0 0 30px;
text-align: left;
}
ul.keywordmatches li.goodmatch a {
font-weight: bold;
}
/* -- index page ------------------------------------------------------------ */
table.contentstable {
width: 90%;
margin-left: auto;
margin-right: auto;
}
table.contentstable p.biglink {
line-height: 150%;
}
a.biglink {
font-size: 1.3em;
}
span.linkdescr {
font-style: italic;
padding-top: 5px;
font-size: 90%;
}
/* -- general index --------------------------------------------------------- */
table.indextable {
width: 100%;
}
table.indextable td {
text-align: left;
vertical-align: top;
}
table.indextable ul {
margin-top: 0;
margin-bottom: 0;
list-style-type: none;
}
table.indextable > tbody > tr > td > ul {
padding-left: 0em;
}
table.indextable tr.pcap {
height: 10px;
}
table.indextable tr.cap {
margin-top: 10px;
background-color: #f2f2f2;
}
img.toggler {
margin-right: 3px;
margin-top: 3px;
cursor: pointer;
}
div.modindex-jumpbox {
border-top: 1px solid #ddd;
border-bottom: 1px solid #ddd;
margin: 1em 0 1em 0;
padding: 0.4em;
}
div.genindex-jumpbox {
border-top: 1px solid #ddd;
border-bottom: 1px solid #ddd;
margin: 1em 0 1em 0;
padding: 0.4em;
}
/* -- domain module index --------------------------------------------------- */
table.modindextable td {
padding: 2px;
border-collapse: collapse;
}
/* -- general body styles --------------------------------------------------- */
div.body {
min-width: 360px;
max-width: 800px;
}
div.body p, div.body dd, div.body li, div.body blockquote {
-moz-hyphens: auto;
-ms-hyphens: auto;
-webkit-hyphens: auto;
hyphens: auto;
}
a.headerlink {
visibility: hidden;
}
a:visited {
color: #551A8B;
}
h1:hover > a.headerlink,
h2:hover > a.headerlink,
h3:hover > a.headerlink,
h4:hover > a.headerlink,
h5:hover > a.headerlink,
h6:hover > a.headerlink,
dt:hover > a.headerlink,
caption:hover > a.headerlink,
p.caption:hover > a.headerlink,
div.code-block-caption:hover > a.headerlink {
visibility: visible;
}
div.body p.caption {
text-align: inherit;
}
div.body td {
text-align: left;
}
.first {
margin-top: 0 !important;
}
p.rubric {
margin-top: 30px;
font-weight: bold;
}
img.align-left, figure.align-left, .figure.align-left, object.align-left {
clear: left;
float: left;
margin-right: 1em;
}
img.align-right, figure.align-right, .figure.align-right, object.align-right {
clear: right;
float: right;
margin-left: 1em;
}
img.align-center, figure.align-center, .figure.align-center, object.align-center {
display: block;
margin-left: auto;
margin-right: auto;
}
img.align-default, figure.align-default, .figure.align-default {
display: block;
margin-left: auto;
margin-right: auto;
}
.align-left {
text-align: left;
}
.align-center {
text-align: center;
}
.align-default {
text-align: center;
}
.align-right {
text-align: right;
}
/* -- sidebars -------------------------------------------------------------- */
div.sidebar,
aside.sidebar {
margin: 0 0 0.5em 1em;
border: 1px solid #ddb;
padding: 7px;
background-color: #ffe;
width: 40%;
float: right;
clear: right;
overflow-x: auto;
}
p.sidebar-title {
font-weight: bold;
}
nav.contents,
aside.topic,
div.admonition, div.topic, blockquote {
clear: left;
}
/* -- topics ---------------------------------------------------------------- */
nav.contents,
aside.topic,
div.topic {
border: 1px solid #ccc;
padding: 7px;
margin: 10px 0 10px 0;
}
p.topic-title {
font-size: 1.1em;
font-weight: bold;
margin-top: 10px;
}
/* -- admonitions ----------------------------------------------------------- */
div.admonition {
margin-top: 10px;
margin-bottom: 10px;
padding: 7px;
}
div.admonition dt {
font-weight: bold;
}
p.admonition-title {
margin: 0px 10px 5px 0px;
font-weight: bold;
}
div.body p.centered {
text-align: center;
margin-top: 25px;
}
/* -- content of sidebars/topics/admonitions -------------------------------- */
div.sidebar > :last-child,
aside.sidebar > :last-child,
nav.contents > :last-child,
aside.topic > :last-child,
div.topic > :last-child,
div.admonition > :last-child {
margin-bottom: 0;
}
div.sidebar::after,
aside.sidebar::after,
nav.contents::after,
aside.topic::after,
div.topic::after,
div.admonition::after,
blockquote::after {
display: block;
content: '';
clear: both;
}
/* -- tables ---------------------------------------------------------------- */
table.docutils {
margin-top: 10px;
margin-bottom: 10px;
border: 0;
border-collapse: collapse;
}
table.align-center {
margin-left: auto;
margin-right: auto;
}
table.align-default {
margin-left: auto;
margin-right: auto;
}
table caption span.caption-number {
font-style: italic;
}
table caption span.caption-text {
}
table.docutils td, table.docutils th {
padding: 1px 8px 1px 5px;
border-top: 0;
border-left: 0;
border-right: 0;
border-bottom: 1px solid #aaa;
}
th {
text-align: left;
padding-right: 5px;
}
table.citation {
border-left: solid 1px gray;
margin-left: 1px;
}
table.citation td {
border-bottom: none;
}
th > :first-child,
td > :first-child {
margin-top: 0px;
}
th > :last-child,
td > :last-child {
margin-bottom: 0px;
}
/* -- figures --------------------------------------------------------------- */
div.figure, figure {
margin: 0.5em;
padding: 0.5em;
}
div.figure p.caption, figcaption {
padding: 0.3em;
}
div.figure p.caption span.caption-number,
figcaption span.caption-number {
font-style: italic;
}
div.figure p.caption span.caption-text,
figcaption span.caption-text {
}
/* -- field list styles ----------------------------------------------------- */
table.field-list td, table.field-list th {
border: 0 !important;
}
.field-list ul {
margin: 0;
padding-left: 1em;
}
.field-list p {
margin: 0;
}
.field-name {
-moz-hyphens: manual;
-ms-hyphens: manual;
-webkit-hyphens: manual;
hyphens: manual;
}
/* -- hlist styles ---------------------------------------------------------- */
table.hlist {
margin: 1em 0;
}
table.hlist td {
vertical-align: top;
}
/* -- object description styles --------------------------------------------- */
.sig {
font-family: 'Consolas', 'Menlo', 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', monospace;
}
.sig-name, code.descname {
background-color: transparent;
font-weight: bold;
}
.sig-name {
font-size: 1.1em;
}
code.descname {
font-size: 1.2em;
}
.sig-prename, code.descclassname {
background-color: transparent;
}
.optional {
font-size: 1.3em;
}
.sig-paren {
font-size: larger;
}
.sig-param.n {
font-style: italic;
}
/* C++ specific styling */
.sig-inline.c-texpr,
.sig-inline.cpp-texpr {
font-family: unset;
}
.sig.c .k, .sig.c .kt,
.sig.cpp .k, .sig.cpp .kt {
color: #0033B3;
}
.sig.c .m,
.sig.cpp .m {
color: #1750EB;
}
.sig.c .s, .sig.c .sc,
.sig.cpp .s, .sig.cpp .sc {
color: #067D17;
}
/* -- other body styles ----------------------------------------------------- */
ol.arabic {
list-style: decimal;
}
ol.loweralpha {
list-style: lower-alpha;
}
ol.upperalpha {
list-style: upper-alpha;
}
ol.lowerroman {
list-style: lower-roman;
}
ol.upperroman {
list-style: upper-roman;
}
:not(li) > ol > li:first-child > :first-child,
:not(li) > ul > li:first-child > :first-child {
margin-top: 0px;
}
:not(li) > ol > li:last-child > :last-child,
:not(li) > ul > li:last-child > :last-child {
margin-bottom: 0px;
}
ol.simple ol p,
ol.simple ul p,
ul.simple ol p,
ul.simple ul p {
margin-top: 0;
}
ol.simple > li:not(:first-child) > p,
ul.simple > li:not(:first-child) > p {
margin-top: 0;
}
ol.simple p,
ul.simple p {
margin-bottom: 0;
}
aside.footnote > span,
div.citation > span {
float: left;
}
aside.footnote > span:last-of-type,
div.citation > span:last-of-type {
padding-right: 0.5em;
}
aside.footnote > p {
margin-left: 2em;
}
div.citation > p {
margin-left: 4em;
}
aside.footnote > p:last-of-type,
div.citation > p:last-of-type {
margin-bottom: 0em;
}
aside.footnote > p:last-of-type:after,
div.citation > p:last-of-type:after {
content: "";
clear: both;
}
dl.field-list {
display: grid;
grid-template-columns: fit-content(30%) auto;
}
dl.field-list > dt {
font-weight: bold;
word-break: break-word;
padding-left: 0.5em;
padding-right: 5px;
}
dl.field-list > dd {
padding-left: 0.5em;
margin-top: 0em;
margin-left: 0em;
margin-bottom: 0em;
}
dl {
margin-bottom: 15px;
}
dd > :first-child {
margin-top: 0px;
}
dd ul, dd table {
margin-bottom: 10px;
}
dd {
margin-top: 3px;
margin-bottom: 10px;
margin-left: 30px;
}
.sig dd {
margin-top: 0px;
margin-bottom: 0px;
}
.sig dl {
margin-top: 0px;
margin-bottom: 0px;
}
dl > dd:last-child,
dl > dd:last-child > :last-child {
margin-bottom: 0;
}
dt:target, span.highlighted {
background-color: #fbe54e;
}
rect.highlighted {
fill: #fbe54e;
}
dl.glossary dt {
font-weight: bold;
font-size: 1.1em;
}
.versionmodified {
font-style: italic;
}
.system-message {
background-color: #fda;
padding: 5px;
border: 3px solid red;
}
.footnote:target {
background-color: #ffa;
}
.line-block {
display: block;
margin-top: 1em;
margin-bottom: 1em;
}
.line-block .line-block {
margin-top: 0;
margin-bottom: 0;
margin-left: 1.5em;
}
.guilabel, .menuselection {
font-family: sans-serif;
}
.accelerator {
text-decoration: underline;
}
.classifier {
font-style: oblique;
}
.classifier:before {
font-style: normal;
margin: 0 0.5em;
content: ":";
display: inline-block;
}
abbr, acronym {
border-bottom: dotted 1px;
cursor: help;
}
.translated {
background-color: rgba(207, 255, 207, 0.2)
}
.untranslated {
background-color: rgba(255, 207, 207, 0.2)
}
/* -- code displays --------------------------------------------------------- */
pre {
overflow: auto;
overflow-y: hidden; /* fixes display issues on Chrome browsers */
}
pre, div[class*="highlight-"] {
clear: both;
}
span.pre {
-moz-hyphens: none;
-ms-hyphens: none;
-webkit-hyphens: none;
hyphens: none;
white-space: nowrap;
}
div[class*="highlight-"] {
margin: 1em 0;
}
td.linenos pre {
border: 0;
background-color: transparent;
color: #aaa;
}
table.highlighttable {
display: block;
}
table.highlighttable tbody {
display: block;
}
table.highlighttable tr {
display: flex;
}
table.highlighttable td {
margin: 0;
padding: 0;
}
table.highlighttable td.linenos {
padding-right: 0.5em;
}
table.highlighttable td.code {
flex: 1;
overflow: hidden;
}
.highlight .hll {
display: block;
}
div.highlight pre,
table.highlighttable pre {
margin: 0;
}
div.code-block-caption + div {
margin-top: 0;
}
div.code-block-caption {
margin-top: 1em;
padding: 2px 5px;
font-size: small;
}
div.code-block-caption code {
background-color: transparent;
}
table.highlighttable td.linenos,
span.linenos,
div.highlight span.gp { /* gp: Generic.Prompt */
user-select: none;
-webkit-user-select: text; /* Safari fallback only */
-webkit-user-select: none; /* Chrome/Safari */
-moz-user-select: none; /* Firefox */
-ms-user-select: none; /* IE10+ */
}
div.code-block-caption span.caption-number {
padding: 0.1em 0.3em;
font-style: italic;
}
div.code-block-caption span.caption-text {
}
div.literal-block-wrapper {
margin: 1em 0;
}
code.xref, a code {
background-color: transparent;
font-weight: bold;
}
h1 code, h2 code, h3 code, h4 code, h5 code, h6 code {
background-color: transparent;
}
.viewcode-link {
float: right;
}
.viewcode-back {
float: right;
font-family: sans-serif;
}
div.viewcode-block:target {
margin: -1px -10px;
padding: 0 10px;
}
/* -- math display ---------------------------------------------------------- */
img.math {
vertical-align: middle;
}
div.body div.math p {
text-align: center;
}
span.eqno {
float: right;
}
span.eqno a.headerlink {
position: absolute;
z-index: 1;
}
div.math:hover a.headerlink {
visibility: visible;
}
/* -- printout stylesheet --------------------------------------------------- */
@media print {
div.document,
div.documentwrapper,
div.bodywrapper {
margin: 0 !important;
width: 100%;
}
div.sphinxsidebar,
div.related,
div.footer,
#top-link {
display: none;
}
}
+1
View File
@@ -0,0 +1 @@
/* This file intentionally left blank. */
+156
View File
@@ -0,0 +1,156 @@
/*
* doctools.js
* ~~~~~~~~~~~
*
* Base JavaScript utilities for all Sphinx HTML documentation.
*
* :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
* :license: BSD, see LICENSE for details.
*
*/
"use strict";
const BLACKLISTED_KEY_CONTROL_ELEMENTS = new Set([
"TEXTAREA",
"INPUT",
"SELECT",
"BUTTON",
]);
const _ready = (callback) => {
if (document.readyState !== "loading") {
callback();
} else {
document.addEventListener("DOMContentLoaded", callback);
}
};
/**
* Small JavaScript module for the documentation.
*/
const Documentation = {
init: () => {
Documentation.initDomainIndexTable();
Documentation.initOnKeyListeners();
},
/**
* i18n support
*/
TRANSLATIONS: {},
PLURAL_EXPR: (n) => (n === 1 ? 0 : 1),
LOCALE: "unknown",
// gettext and ngettext don't access this so that the functions
// can safely bound to a different name (_ = Documentation.gettext)
gettext: (string) => {
const translated = Documentation.TRANSLATIONS[string];
switch (typeof translated) {
case "undefined":
return string; // no translation
case "string":
return translated; // translation exists
default:
return translated[0]; // (singular, plural) translation tuple exists
}
},
ngettext: (singular, plural, n) => {
const translated = Documentation.TRANSLATIONS[singular];
if (typeof translated !== "undefined")
return translated[Documentation.PLURAL_EXPR(n)];
return n === 1 ? singular : plural;
},
addTranslations: (catalog) => {
Object.assign(Documentation.TRANSLATIONS, catalog.messages);
Documentation.PLURAL_EXPR = new Function(
"n",
`return (${catalog.plural_expr})`
);
Documentation.LOCALE = catalog.locale;
},
/**
* helper function to focus on search bar
*/
focusSearchBar: () => {
document.querySelectorAll("input[name=q]")[0]?.focus();
},
/**
* Initialise the domain index toggle buttons
*/
initDomainIndexTable: () => {
const toggler = (el) => {
const idNumber = el.id.substr(7);
const toggledRows = document.querySelectorAll(`tr.cg-${idNumber}`);
if (el.src.substr(-9) === "minus.png") {
el.src = `${el.src.substr(0, el.src.length - 9)}plus.png`;
toggledRows.forEach((el) => (el.style.display = "none"));
} else {
el.src = `${el.src.substr(0, el.src.length - 8)}minus.png`;
toggledRows.forEach((el) => (el.style.display = ""));
}
};
const togglerElements = document.querySelectorAll("img.toggler");
togglerElements.forEach((el) =>
el.addEventListener("click", (event) => toggler(event.currentTarget))
);
togglerElements.forEach((el) => (el.style.display = ""));
if (DOCUMENTATION_OPTIONS.COLLAPSE_INDEX) togglerElements.forEach(toggler);
},
initOnKeyListeners: () => {
// only install a listener if it is really needed
if (
!DOCUMENTATION_OPTIONS.NAVIGATION_WITH_KEYS &&
!DOCUMENTATION_OPTIONS.ENABLE_SEARCH_SHORTCUTS
)
return;
document.addEventListener("keydown", (event) => {
// bail for input elements
if (BLACKLISTED_KEY_CONTROL_ELEMENTS.has(document.activeElement.tagName)) return;
// bail with special keys
if (event.altKey || event.ctrlKey || event.metaKey) return;
if (!event.shiftKey) {
switch (event.key) {
case "ArrowLeft":
if (!DOCUMENTATION_OPTIONS.NAVIGATION_WITH_KEYS) break;
const prevLink = document.querySelector('link[rel="prev"]');
if (prevLink && prevLink.href) {
window.location.href = prevLink.href;
event.preventDefault();
}
break;
case "ArrowRight":
if (!DOCUMENTATION_OPTIONS.NAVIGATION_WITH_KEYS) break;
const nextLink = document.querySelector('link[rel="next"]');
if (nextLink && nextLink.href) {
window.location.href = nextLink.href;
event.preventDefault();
}
break;
}
}
// some keyboard layouts may need Shift to get /
switch (event.key) {
case "/":
if (!DOCUMENTATION_OPTIONS.ENABLE_SEARCH_SHORTCUTS) break;
Documentation.focusSearchBar();
event.preventDefault();
}
});
},
};
// quick alias for translations
const _ = Documentation.gettext;
_ready(Documentation.init);
@@ -0,0 +1,13 @@
const DOCUMENTATION_OPTIONS = {
VERSION: '',
LANGUAGE: 'en',
COLLAPSE_INDEX: false,
BUILDER: 'html',
FILE_SUFFIX: '.html',
LINK_SUFFIX: '.html',
HAS_SOURCE: true,
SOURCELINK_SUFFIX: '.txt',
NAVIGATION_WITH_KEYS: false,
SHOW_SEARCH_SUMMARY: true,
ENABLE_SEARCH_SHORTCUTS: true,
};
Binary file not shown.

After

Width:  |  Height:  |  Size: 286 B

+199
View File
@@ -0,0 +1,199 @@
/*
* language_data.js
* ~~~~~~~~~~~~~~~~
*
* This script contains the language-specific data used by searchtools.js,
* namely the list of stopwords, stemmer, scorer and splitter.
*
* :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
* :license: BSD, see LICENSE for details.
*
*/
var stopwords = ["a", "and", "are", "as", "at", "be", "but", "by", "for", "if", "in", "into", "is", "it", "near", "no", "not", "of", "on", "or", "such", "that", "the", "their", "then", "there", "these", "they", "this", "to", "was", "will", "with"];
/* Non-minified version is copied as a separate JS file, is available */
/**
* Porter Stemmer
*/
var Stemmer = function() {
var step2list = {
ational: 'ate',
tional: 'tion',
enci: 'ence',
anci: 'ance',
izer: 'ize',
bli: 'ble',
alli: 'al',
entli: 'ent',
eli: 'e',
ousli: 'ous',
ization: 'ize',
ation: 'ate',
ator: 'ate',
alism: 'al',
iveness: 'ive',
fulness: 'ful',
ousness: 'ous',
aliti: 'al',
iviti: 'ive',
biliti: 'ble',
logi: 'log'
};
var step3list = {
icate: 'ic',
ative: '',
alize: 'al',
iciti: 'ic',
ical: 'ic',
ful: '',
ness: ''
};
var c = "[^aeiou]"; // consonant
var v = "[aeiouy]"; // vowel
var C = c + "[^aeiouy]*"; // consonant sequence
var V = v + "[aeiou]*"; // vowel sequence
var mgr0 = "^(" + C + ")?" + V + C; // [C]VC... is m>0
var meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$"; // [C]VC[V] is m=1
var mgr1 = "^(" + C + ")?" + V + C + V + C; // [C]VCVC... is m>1
var s_v = "^(" + C + ")?" + v; // vowel in stem
this.stemWord = function (w) {
var stem;
var suffix;
var firstch;
var origword = w;
if (w.length < 3)
return w;
var re;
var re2;
var re3;
var re4;
firstch = w.substr(0,1);
if (firstch == "y")
w = firstch.toUpperCase() + w.substr(1);
// Step 1a
re = /^(.+?)(ss|i)es$/;
re2 = /^(.+?)([^s])s$/;
if (re.test(w))
w = w.replace(re,"$1$2");
else if (re2.test(w))
w = w.replace(re2,"$1$2");
// Step 1b
re = /^(.+?)eed$/;
re2 = /^(.+?)(ed|ing)$/;
if (re.test(w)) {
var fp = re.exec(w);
re = new RegExp(mgr0);
if (re.test(fp[1])) {
re = /.$/;
w = w.replace(re,"");
}
}
else if (re2.test(w)) {
var fp = re2.exec(w);
stem = fp[1];
re2 = new RegExp(s_v);
if (re2.test(stem)) {
w = stem;
re2 = /(at|bl|iz)$/;
re3 = new RegExp("([^aeiouylsz])\\1$");
re4 = new RegExp("^" + C + v + "[^aeiouwxy]$");
if (re2.test(w))
w = w + "e";
else if (re3.test(w)) {
re = /.$/;
w = w.replace(re,"");
}
else if (re4.test(w))
w = w + "e";
}
}
// Step 1c
re = /^(.+?)y$/;
if (re.test(w)) {
var fp = re.exec(w);
stem = fp[1];
re = new RegExp(s_v);
if (re.test(stem))
w = stem + "i";
}
// Step 2
re = /^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/;
if (re.test(w)) {
var fp = re.exec(w);
stem = fp[1];
suffix = fp[2];
re = new RegExp(mgr0);
if (re.test(stem))
w = stem + step2list[suffix];
}
// Step 3
re = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/;
if (re.test(w)) {
var fp = re.exec(w);
stem = fp[1];
suffix = fp[2];
re = new RegExp(mgr0);
if (re.test(stem))
w = stem + step3list[suffix];
}
// Step 4
re = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/;
re2 = /^(.+?)(s|t)(ion)$/;
if (re.test(w)) {
var fp = re.exec(w);
stem = fp[1];
re = new RegExp(mgr1);
if (re.test(stem))
w = stem;
}
else if (re2.test(w)) {
var fp = re2.exec(w);
stem = fp[1] + fp[2];
re2 = new RegExp(mgr1);
if (re2.test(stem))
w = stem;
}
// Step 5
re = /^(.+?)e$/;
if (re.test(w)) {
var fp = re.exec(w);
stem = fp[1];
re = new RegExp(mgr1);
re2 = new RegExp(meq1);
re3 = new RegExp("^" + C + v + "[^aeiouwxy]$");
if (re.test(stem) || (re2.test(stem) && !(re3.test(stem))))
w = stem;
}
re = /ll$/;
re2 = new RegExp(mgr1);
if (re.test(w) && re2.test(w)) {
re = /.$/;
w = w.replace(re,"");
}
// and turn initial Y back to y
if (firstch == "y")
w = firstch.toLowerCase() + w.substr(1);
return w;
}
}
Binary file not shown.

After

Width:  |  Height:  |  Size: 90 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 90 B

+84
View File
@@ -0,0 +1,84 @@
pre { line-height: 125%; }
td.linenos .normal { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
span.linenos { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
td.linenos .special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
span.linenos.special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
.highlight .hll { background-color: #ffffcc }
.highlight { background: #f8f8f8; }
.highlight .c { color: #8f5902; font-style: italic } /* Comment */
.highlight .err { color: #a40000; border: 1px solid #ef2929 } /* Error */
.highlight .g { color: #000000 } /* Generic */
.highlight .k { color: #004461; font-weight: bold } /* Keyword */
.highlight .l { color: #000000 } /* Literal */
.highlight .n { color: #000000 } /* Name */
.highlight .o { color: #582800 } /* Operator */
.highlight .x { color: #000000 } /* Other */
.highlight .p { color: #000000; font-weight: bold } /* Punctuation */
.highlight .ch { color: #8f5902; font-style: italic } /* Comment.Hashbang */
.highlight .cm { color: #8f5902; font-style: italic } /* Comment.Multiline */
.highlight .cp { color: #8f5902 } /* Comment.Preproc */
.highlight .cpf { color: #8f5902; font-style: italic } /* Comment.PreprocFile */
.highlight .c1 { color: #8f5902; font-style: italic } /* Comment.Single */
.highlight .cs { color: #8f5902; font-style: italic } /* Comment.Special */
.highlight .gd { color: #a40000 } /* Generic.Deleted */
.highlight .ge { color: #000000; font-style: italic } /* Generic.Emph */
.highlight .ges { color: #000000 } /* Generic.EmphStrong */
.highlight .gr { color: #ef2929 } /* Generic.Error */
.highlight .gh { color: #000080; font-weight: bold } /* Generic.Heading */
.highlight .gi { color: #00A000 } /* Generic.Inserted */
.highlight .go { color: #888888 } /* Generic.Output */
.highlight .gp { color: #745334 } /* Generic.Prompt */
.highlight .gs { color: #000000; font-weight: bold } /* Generic.Strong */
.highlight .gu { color: #800080; font-weight: bold } /* Generic.Subheading */
.highlight .gt { color: #a40000; font-weight: bold } /* Generic.Traceback */
.highlight .kc { color: #004461; font-weight: bold } /* Keyword.Constant */
.highlight .kd { color: #004461; font-weight: bold } /* Keyword.Declaration */
.highlight .kn { color: #004461; font-weight: bold } /* Keyword.Namespace */
.highlight .kp { color: #004461; font-weight: bold } /* Keyword.Pseudo */
.highlight .kr { color: #004461; font-weight: bold } /* Keyword.Reserved */
.highlight .kt { color: #004461; font-weight: bold } /* Keyword.Type */
.highlight .ld { color: #000000 } /* Literal.Date */
.highlight .m { color: #990000 } /* Literal.Number */
.highlight .s { color: #4e9a06 } /* Literal.String */
.highlight .na { color: #c4a000 } /* Name.Attribute */
.highlight .nb { color: #004461 } /* Name.Builtin */
.highlight .nc { color: #000000 } /* Name.Class */
.highlight .no { color: #000000 } /* Name.Constant */
.highlight .nd { color: #888888 } /* Name.Decorator */
.highlight .ni { color: #ce5c00 } /* Name.Entity */
.highlight .ne { color: #cc0000; font-weight: bold } /* Name.Exception */
.highlight .nf { color: #000000 } /* Name.Function */
.highlight .nl { color: #f57900 } /* Name.Label */
.highlight .nn { color: #000000 } /* Name.Namespace */
.highlight .nx { color: #000000 } /* Name.Other */
.highlight .py { color: #000000 } /* Name.Property */
.highlight .nt { color: #004461; font-weight: bold } /* Name.Tag */
.highlight .nv { color: #000000 } /* Name.Variable */
.highlight .ow { color: #004461; font-weight: bold } /* Operator.Word */
.highlight .pm { color: #000000; font-weight: bold } /* Punctuation.Marker */
.highlight .w { color: #f8f8f8; text-decoration: underline } /* Text.Whitespace */
.highlight .mb { color: #990000 } /* Literal.Number.Bin */
.highlight .mf { color: #990000 } /* Literal.Number.Float */
.highlight .mh { color: #990000 } /* Literal.Number.Hex */
.highlight .mi { color: #990000 } /* Literal.Number.Integer */
.highlight .mo { color: #990000 } /* Literal.Number.Oct */
.highlight .sa { color: #4e9a06 } /* Literal.String.Affix */
.highlight .sb { color: #4e9a06 } /* Literal.String.Backtick */
.highlight .sc { color: #4e9a06 } /* Literal.String.Char */
.highlight .dl { color: #4e9a06 } /* Literal.String.Delimiter */
.highlight .sd { color: #8f5902; font-style: italic } /* Literal.String.Doc */
.highlight .s2 { color: #4e9a06 } /* Literal.String.Double */
.highlight .se { color: #4e9a06 } /* Literal.String.Escape */
.highlight .sh { color: #4e9a06 } /* Literal.String.Heredoc */
.highlight .si { color: #4e9a06 } /* Literal.String.Interpol */
.highlight .sx { color: #4e9a06 } /* Literal.String.Other */
.highlight .sr { color: #4e9a06 } /* Literal.String.Regex */
.highlight .s1 { color: #4e9a06 } /* Literal.String.Single */
.highlight .ss { color: #4e9a06 } /* Literal.String.Symbol */
.highlight .bp { color: #3465a4 } /* Name.Builtin.Pseudo */
.highlight .fm { color: #000000 } /* Name.Function.Magic */
.highlight .vc { color: #000000 } /* Name.Variable.Class */
.highlight .vg { color: #000000 } /* Name.Variable.Global */
.highlight .vi { color: #000000 } /* Name.Variable.Instance */
.highlight .vm { color: #000000 } /* Name.Variable.Magic */
.highlight .il { color: #990000 } /* Literal.Number.Integer.Long */
+574
View File
@@ -0,0 +1,574 @@
/*
* searchtools.js
* ~~~~~~~~~~~~~~~~
*
* Sphinx JavaScript utilities for the full-text search.
*
* :copyright: Copyright 2007-2023 by the Sphinx team, see AUTHORS.
* :license: BSD, see LICENSE for details.
*
*/
"use strict";
/**
* Simple result scoring code.
*/
if (typeof Scorer === "undefined") {
var Scorer = {
// Implement the following function to further tweak the score for each result
// The function takes a result array [docname, title, anchor, descr, score, filename]
// and returns the new score.
/*
score: result => {
const [docname, title, anchor, descr, score, filename] = result
return score
},
*/
// query matches the full name of an object
objNameMatch: 11,
// or matches in the last dotted part of the object name
objPartialMatch: 6,
// Additive scores depending on the priority of the object
objPrio: {
0: 15, // used to be importantResults
1: 5, // used to be objectResults
2: -5, // used to be unimportantResults
},
// Used when the priority is not in the mapping.
objPrioDefault: 0,
// query found in title
title: 15,
partialTitle: 7,
// query found in terms
term: 5,
partialTerm: 2,
};
}
const _removeChildren = (element) => {
while (element && element.lastChild) element.removeChild(element.lastChild);
};
/**
* See https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Regular_Expressions#escaping
*/
const _escapeRegExp = (string) =>
string.replace(/[.*+\-?^${}()|[\]\\]/g, "\\$&"); // $& means the whole matched string
const _displayItem = (item, searchTerms, highlightTerms) => {
const docBuilder = DOCUMENTATION_OPTIONS.BUILDER;
const docFileSuffix = DOCUMENTATION_OPTIONS.FILE_SUFFIX;
const docLinkSuffix = DOCUMENTATION_OPTIONS.LINK_SUFFIX;
const showSearchSummary = DOCUMENTATION_OPTIONS.SHOW_SEARCH_SUMMARY;
const contentRoot = document.documentElement.dataset.content_root;
const [docName, title, anchor, descr, score, _filename] = item;
let listItem = document.createElement("li");
let requestUrl;
let linkUrl;
if (docBuilder === "dirhtml") {
// dirhtml builder
let dirname = docName + "/";
if (dirname.match(/\/index\/$/))
dirname = dirname.substring(0, dirname.length - 6);
else if (dirname === "index/") dirname = "";
requestUrl = contentRoot + dirname;
linkUrl = requestUrl;
} else {
// normal html builders
requestUrl = contentRoot + docName + docFileSuffix;
linkUrl = docName + docLinkSuffix;
}
let linkEl = listItem.appendChild(document.createElement("a"));
linkEl.href = linkUrl + anchor;
linkEl.dataset.score = score;
linkEl.innerHTML = title;
if (descr) {
listItem.appendChild(document.createElement("span")).innerHTML =
" (" + descr + ")";
// highlight search terms in the description
if (SPHINX_HIGHLIGHT_ENABLED) // set in sphinx_highlight.js
highlightTerms.forEach((term) => _highlightText(listItem, term, "highlighted"));
}
else if (showSearchSummary)
fetch(requestUrl)
.then((responseData) => responseData.text())
.then((data) => {
if (data)
listItem.appendChild(
Search.makeSearchSummary(data, searchTerms)
);
// highlight search terms in the summary
if (SPHINX_HIGHLIGHT_ENABLED) // set in sphinx_highlight.js
highlightTerms.forEach((term) => _highlightText(listItem, term, "highlighted"));
});
Search.output.appendChild(listItem);
};
const _finishSearch = (resultCount) => {
Search.stopPulse();
Search.title.innerText = _("Search Results");
if (!resultCount)
Search.status.innerText = Documentation.gettext(
"Your search did not match any documents. Please make sure that all words are spelled correctly and that you've selected enough categories."
);
else
Search.status.innerText = _(
`Search finished, found ${resultCount} page(s) matching the search query.`
);
};
const _displayNextItem = (
results,
resultCount,
searchTerms,
highlightTerms,
) => {
// results left, load the summary and display it
// this is intended to be dynamic (don't sub resultsCount)
if (results.length) {
_displayItem(results.pop(), searchTerms, highlightTerms);
setTimeout(
() => _displayNextItem(results, resultCount, searchTerms, highlightTerms),
5
);
}
// search finished, update title and status message
else _finishSearch(resultCount);
};
/**
* Default splitQuery function. Can be overridden in ``sphinx.search`` with a
* custom function per language.
*
* The regular expression works by splitting the string on consecutive characters
* that are not Unicode letters, numbers, underscores, or emoji characters.
* This is the same as ``\W+`` in Python, preserving the surrogate pair area.
*/
if (typeof splitQuery === "undefined") {
var splitQuery = (query) => query
.split(/[^\p{Letter}\p{Number}_\p{Emoji_Presentation}]+/gu)
.filter(term => term) // remove remaining empty strings
}
/**
* Search Module
*/
const Search = {
_index: null,
_queued_query: null,
_pulse_status: -1,
htmlToText: (htmlString) => {
const htmlElement = new DOMParser().parseFromString(htmlString, 'text/html');
htmlElement.querySelectorAll(".headerlink").forEach((el) => { el.remove() });
const docContent = htmlElement.querySelector('[role="main"]');
if (docContent !== undefined) return docContent.textContent;
console.warn(
"Content block not found. Sphinx search tries to obtain it via '[role=main]'. Could you check your theme or template."
);
return "";
},
init: () => {
const query = new URLSearchParams(window.location.search).get("q");
document
.querySelectorAll('input[name="q"]')
.forEach((el) => (el.value = query));
if (query) Search.performSearch(query);
},
loadIndex: (url) =>
(document.body.appendChild(document.createElement("script")).src = url),
setIndex: (index) => {
Search._index = index;
if (Search._queued_query !== null) {
const query = Search._queued_query;
Search._queued_query = null;
Search.query(query);
}
},
hasIndex: () => Search._index !== null,
deferQuery: (query) => (Search._queued_query = query),
stopPulse: () => (Search._pulse_status = -1),
startPulse: () => {
if (Search._pulse_status >= 0) return;
const pulse = () => {
Search._pulse_status = (Search._pulse_status + 1) % 4;
Search.dots.innerText = ".".repeat(Search._pulse_status);
if (Search._pulse_status >= 0) window.setTimeout(pulse, 500);
};
pulse();
},
/**
* perform a search for something (or wait until index is loaded)
*/
performSearch: (query) => {
// create the required interface elements
const searchText = document.createElement("h2");
searchText.textContent = _("Searching");
const searchSummary = document.createElement("p");
searchSummary.classList.add("search-summary");
searchSummary.innerText = "";
const searchList = document.createElement("ul");
searchList.classList.add("search");
const out = document.getElementById("search-results");
Search.title = out.appendChild(searchText);
Search.dots = Search.title.appendChild(document.createElement("span"));
Search.status = out.appendChild(searchSummary);
Search.output = out.appendChild(searchList);
const searchProgress = document.getElementById("search-progress");
// Some themes don't use the search progress node
if (searchProgress) {
searchProgress.innerText = _("Preparing search...");
}
Search.startPulse();
// index already loaded, the browser was quick!
if (Search.hasIndex()) Search.query(query);
else Search.deferQuery(query);
},
/**
* execute search (requires search index to be loaded)
*/
query: (query) => {
const filenames = Search._index.filenames;
const docNames = Search._index.docnames;
const titles = Search._index.titles;
const allTitles = Search._index.alltitles;
const indexEntries = Search._index.indexentries;
// stem the search terms and add them to the correct list
const stemmer = new Stemmer();
const searchTerms = new Set();
const excludedTerms = new Set();
const highlightTerms = new Set();
const objectTerms = new Set(splitQuery(query.toLowerCase().trim()));
splitQuery(query.trim()).forEach((queryTerm) => {
const queryTermLower = queryTerm.toLowerCase();
// maybe skip this "word"
// stopwords array is from language_data.js
if (
stopwords.indexOf(queryTermLower) !== -1 ||
queryTerm.match(/^\d+$/)
)
return;
// stem the word
let word = stemmer.stemWord(queryTermLower);
// select the correct list
if (word[0] === "-") excludedTerms.add(word.substr(1));
else {
searchTerms.add(word);
highlightTerms.add(queryTermLower);
}
});
if (SPHINX_HIGHLIGHT_ENABLED) { // set in sphinx_highlight.js
localStorage.setItem("sphinx_highlight_terms", [...highlightTerms].join(" "))
}
// console.debug("SEARCH: searching for:");
// console.info("required: ", [...searchTerms]);
// console.info("excluded: ", [...excludedTerms]);
// array of [docname, title, anchor, descr, score, filename]
let results = [];
_removeChildren(document.getElementById("search-progress"));
const queryLower = query.toLowerCase();
for (const [title, foundTitles] of Object.entries(allTitles)) {
if (title.toLowerCase().includes(queryLower) && (queryLower.length >= title.length/2)) {
for (const [file, id] of foundTitles) {
let score = Math.round(100 * queryLower.length / title.length)
results.push([
docNames[file],
titles[file] !== title ? `${titles[file]} > ${title}` : title,
id !== null ? "#" + id : "",
null,
score,
filenames[file],
]);
}
}
}
// search for explicit entries in index directives
for (const [entry, foundEntries] of Object.entries(indexEntries)) {
if (entry.includes(queryLower) && (queryLower.length >= entry.length/2)) {
for (const [file, id] of foundEntries) {
let score = Math.round(100 * queryLower.length / entry.length)
results.push([
docNames[file],
titles[file],
id ? "#" + id : "",
null,
score,
filenames[file],
]);
}
}
}
// lookup as object
objectTerms.forEach((term) =>
results.push(...Search.performObjectSearch(term, objectTerms))
);
// lookup as search terms in fulltext
results.push(...Search.performTermsSearch(searchTerms, excludedTerms));
// let the scorer override scores with a custom scoring function
if (Scorer.score) results.forEach((item) => (item[4] = Scorer.score(item)));
// now sort the results by score (in opposite order of appearance, since the
// display function below uses pop() to retrieve items) and then
// alphabetically
results.sort((a, b) => {
const leftScore = a[4];
const rightScore = b[4];
if (leftScore === rightScore) {
// same score: sort alphabetically
const leftTitle = a[1].toLowerCase();
const rightTitle = b[1].toLowerCase();
if (leftTitle === rightTitle) return 0;
return leftTitle > rightTitle ? -1 : 1; // inverted is intentional
}
return leftScore > rightScore ? 1 : -1;
});
// remove duplicate search results
// note the reversing of results, so that in the case of duplicates, the highest-scoring entry is kept
let seen = new Set();
results = results.reverse().reduce((acc, result) => {
let resultStr = result.slice(0, 4).concat([result[5]]).map(v => String(v)).join(',');
if (!seen.has(resultStr)) {
acc.push(result);
seen.add(resultStr);
}
return acc;
}, []);
results = results.reverse();
// for debugging
//Search.lastresults = results.slice(); // a copy
// console.info("search results:", Search.lastresults);
// print the results
_displayNextItem(results, results.length, searchTerms, highlightTerms);
},
/**
* search for object names
*/
performObjectSearch: (object, objectTerms) => {
const filenames = Search._index.filenames;
const docNames = Search._index.docnames;
const objects = Search._index.objects;
const objNames = Search._index.objnames;
const titles = Search._index.titles;
const results = [];
const objectSearchCallback = (prefix, match) => {
const name = match[4]
const fullname = (prefix ? prefix + "." : "") + name;
const fullnameLower = fullname.toLowerCase();
if (fullnameLower.indexOf(object) < 0) return;
let score = 0;
const parts = fullnameLower.split(".");
// check for different match types: exact matches of full name or
// "last name" (i.e. last dotted part)
if (fullnameLower === object || parts.slice(-1)[0] === object)
score += Scorer.objNameMatch;
else if (parts.slice(-1)[0].indexOf(object) > -1)
score += Scorer.objPartialMatch; // matches in last name
const objName = objNames[match[1]][2];
const title = titles[match[0]];
// If more than one term searched for, we require other words to be
// found in the name/title/description
const otherTerms = new Set(objectTerms);
otherTerms.delete(object);
if (otherTerms.size > 0) {
const haystack = `${prefix} ${name} ${objName} ${title}`.toLowerCase();
if (
[...otherTerms].some((otherTerm) => haystack.indexOf(otherTerm) < 0)
)
return;
}
let anchor = match[3];
if (anchor === "") anchor = fullname;
else if (anchor === "-") anchor = objNames[match[1]][1] + "-" + fullname;
const descr = objName + _(", in ") + title;
// add custom score for some objects according to scorer
if (Scorer.objPrio.hasOwnProperty(match[2]))
score += Scorer.objPrio[match[2]];
else score += Scorer.objPrioDefault;
results.push([
docNames[match[0]],
fullname,
"#" + anchor,
descr,
score,
filenames[match[0]],
]);
};
Object.keys(objects).forEach((prefix) =>
objects[prefix].forEach((array) =>
objectSearchCallback(prefix, array)
)
);
return results;
},
/**
* search for full-text terms in the index
*/
performTermsSearch: (searchTerms, excludedTerms) => {
// prepare search
const terms = Search._index.terms;
const titleTerms = Search._index.titleterms;
const filenames = Search._index.filenames;
const docNames = Search._index.docnames;
const titles = Search._index.titles;
const scoreMap = new Map();
const fileMap = new Map();
// perform the search on the required terms
searchTerms.forEach((word) => {
const files = [];
const arr = [
{ files: terms[word], score: Scorer.term },
{ files: titleTerms[word], score: Scorer.title },
];
// add support for partial matches
if (word.length > 2) {
const escapedWord = _escapeRegExp(word);
Object.keys(terms).forEach((term) => {
if (term.match(escapedWord) && !terms[word])
arr.push({ files: terms[term], score: Scorer.partialTerm });
});
Object.keys(titleTerms).forEach((term) => {
if (term.match(escapedWord) && !titleTerms[word])
arr.push({ files: titleTerms[word], score: Scorer.partialTitle });
});
}
// no match but word was a required one
if (arr.every((record) => record.files === undefined)) return;
// found search word in contents
arr.forEach((record) => {
if (record.files === undefined) return;
let recordFiles = record.files;
if (recordFiles.length === undefined) recordFiles = [recordFiles];
files.push(...recordFiles);
// set score for the word in each file
recordFiles.forEach((file) => {
if (!scoreMap.has(file)) scoreMap.set(file, {});
scoreMap.get(file)[word] = record.score;
});
});
// create the mapping
files.forEach((file) => {
if (fileMap.has(file) && fileMap.get(file).indexOf(word) === -1)
fileMap.get(file).push(word);
else fileMap.set(file, [word]);
});
});
// now check if the files don't contain excluded terms
const results = [];
for (const [file, wordList] of fileMap) {
// check if all requirements are matched
// as search terms with length < 3 are discarded
const filteredTermCount = [...searchTerms].filter(
(term) => term.length > 2
).length;
if (
wordList.length !== searchTerms.size &&
wordList.length !== filteredTermCount
)
continue;
// ensure that none of the excluded terms is in the search result
if (
[...excludedTerms].some(
(term) =>
terms[term] === file ||
titleTerms[term] === file ||
(terms[term] || []).includes(file) ||
(titleTerms[term] || []).includes(file)
)
)
break;
// select one (max) score for the file.
const score = Math.max(...wordList.map((w) => scoreMap.get(file)[w]));
// add result to the result list
results.push([
docNames[file],
titles[file],
"",
null,
score,
filenames[file],
]);
}
return results;
},
/**
* helper function to return a node containing the
* search summary for a given text. keywords is a list
* of stemmed words.
*/
makeSearchSummary: (htmlText, keywords) => {
const text = Search.htmlToText(htmlText);
if (text === "") return null;
const textLower = text.toLowerCase();
const actualStartPosition = [...keywords]
.map((k) => textLower.indexOf(k.toLowerCase()))
.filter((i) => i > -1)
.slice(-1)[0];
const startWithContext = Math.max(actualStartPosition - 120, 0);
const top = startWithContext === 0 ? "" : "...";
const tail = startWithContext + 240 < text.length ? "..." : "";
let summary = document.createElement("p");
summary.classList.add("context");
summary.textContent = top + text.substr(startWithContext, 240).trim() + tail;
return summary;
},
};
_ready(Search.init);
+154
View File
@@ -0,0 +1,154 @@
/* Highlighting utilities for Sphinx HTML documentation. */
"use strict";
const SPHINX_HIGHLIGHT_ENABLED = true
/**
* highlight a given string on a node by wrapping it in
* span elements with the given class name.
*/
const _highlight = (node, addItems, text, className) => {
if (node.nodeType === Node.TEXT_NODE) {
const val = node.nodeValue;
const parent = node.parentNode;
const pos = val.toLowerCase().indexOf(text);
if (
pos >= 0 &&
!parent.classList.contains(className) &&
!parent.classList.contains("nohighlight")
) {
let span;
const closestNode = parent.closest("body, svg, foreignObject");
const isInSVG = closestNode && closestNode.matches("svg");
if (isInSVG) {
span = document.createElementNS("http://www.w3.org/2000/svg", "tspan");
} else {
span = document.createElement("span");
span.classList.add(className);
}
span.appendChild(document.createTextNode(val.substr(pos, text.length)));
const rest = document.createTextNode(val.substr(pos + text.length));
parent.insertBefore(
span,
parent.insertBefore(
rest,
node.nextSibling
)
);
node.nodeValue = val.substr(0, pos);
/* There may be more occurrences of search term in this node. So call this
* function recursively on the remaining fragment.
*/
_highlight(rest, addItems, text, className);
if (isInSVG) {
const rect = document.createElementNS(
"http://www.w3.org/2000/svg",
"rect"
);
const bbox = parent.getBBox();
rect.x.baseVal.value = bbox.x;
rect.y.baseVal.value = bbox.y;
rect.width.baseVal.value = bbox.width;
rect.height.baseVal.value = bbox.height;
rect.setAttribute("class", className);
addItems.push({ parent: parent, target: rect });
}
}
} else if (node.matches && !node.matches("button, select, textarea")) {
node.childNodes.forEach((el) => _highlight(el, addItems, text, className));
}
};
const _highlightText = (thisNode, text, className) => {
let addItems = [];
_highlight(thisNode, addItems, text, className);
addItems.forEach((obj) =>
obj.parent.insertAdjacentElement("beforebegin", obj.target)
);
};
/**
* Small JavaScript module for the documentation.
*/
const SphinxHighlight = {
/**
* highlight the search words provided in localstorage in the text
*/
highlightSearchWords: () => {
if (!SPHINX_HIGHLIGHT_ENABLED) return; // bail if no highlight
// get and clear terms from localstorage
const url = new URL(window.location);
const highlight =
localStorage.getItem("sphinx_highlight_terms")
|| url.searchParams.get("highlight")
|| "";
localStorage.removeItem("sphinx_highlight_terms")
url.searchParams.delete("highlight");
window.history.replaceState({}, "", url);
// get individual terms from highlight string
const terms = highlight.toLowerCase().split(/\s+/).filter(x => x);
if (terms.length === 0) return; // nothing to do
// There should never be more than one element matching "div.body"
const divBody = document.querySelectorAll("div.body");
const body = divBody.length ? divBody[0] : document.querySelector("body");
window.setTimeout(() => {
terms.forEach((term) => _highlightText(body, term, "highlighted"));
}, 10);
const searchBox = document.getElementById("searchbox");
if (searchBox === null) return;
searchBox.appendChild(
document
.createRange()
.createContextualFragment(
'<p class="highlight-link">' +
'<a href="javascript:SphinxHighlight.hideSearchWords()">' +
_("Hide Search Matches") +
"</a></p>"
)
);
},
/**
* helper function to hide the search marks again
*/
hideSearchWords: () => {
document
.querySelectorAll("#searchbox .highlight-link")
.forEach((el) => el.remove());
document
.querySelectorAll("span.highlighted")
.forEach((el) => el.classList.remove("highlighted"));
localStorage.removeItem("sphinx_highlight_terms")
},
initEscapeListener: () => {
// only install a listener if it is really needed
if (!DOCUMENTATION_OPTIONS.ENABLE_SEARCH_SHORTCUTS) return;
document.addEventListener("keydown", (event) => {
// bail for input elements
if (BLACKLISTED_KEY_CONTROL_ELEMENTS.has(document.activeElement.tagName)) return;
// bail with special keys
if (event.shiftKey || event.altKey || event.ctrlKey || event.metaKey) return;
if (DOCUMENTATION_OPTIONS.ENABLE_SEARCH_SHORTCUTS && (event.key === "Escape")) {
SphinxHighlight.hideSearchWords();
event.preventDefault();
}
});
},
};
_ready(() => {
/* Do not call highlightSearchWords() when we are on the search page.
* It will highlight words from the *previous* search query.
*/
if (typeof Search === "undefined") SphinxHighlight.highlightSearchWords();
SphinxHighlight.initEscapeListener();
});
+281
View File
@@ -0,0 +1,281 @@
<!DOCTYPE html>
<html lang="en" data-content_root="./">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Index &#8212; whisper_live documentation</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=4f649999" />
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=039e1c02" />
<script src="_static/documentation_options.js?v=5929fcd5"></script>
<script src="_static/doctools.js?v=888ff710"></script>
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
<link rel="index" title="Index" href="#" />
<link rel="search" title="Search" href="search.html" />
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
<meta name="viewport" content="width=device-width, initial-scale=0.9, maximum-scale=0.9" />
</head><body>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<h1 id="index">Index</h1>
<div class="genindex-jumpbox">
<a href="#A"><strong>A</strong></a>
| <a href="#B"><strong>B</strong></a>
| <a href="#C"><strong>C</strong></a>
| <a href="#D"><strong>D</strong></a>
| <a href="#F"><strong>F</strong></a>
| <a href="#G"><strong>G</strong></a>
| <a href="#M"><strong>M</strong></a>
| <a href="#O"><strong>O</strong></a>
| <a href="#P"><strong>P</strong></a>
| <a href="#R"><strong>R</strong></a>
| <a href="#S"><strong>S</strong></a>
| <a href="#T"><strong>T</strong></a>
| <a href="#U"><strong>U</strong></a>
| <a href="#W"><strong>W</strong></a>
</div>
<h2 id="A">A</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.server.ServeClient.add_frames">add_frames() (whisper_live.server.ServeClient method)</a>
</li>
</ul></td>
</tr></table>
<h2 id="B">B</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.client.Client.bytes_to_float_array">bytes_to_float_array() (whisper_live.client.Client static method)</a>
</li>
</ul></td>
</tr></table>
<h2 id="C">C</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.server.ServeClient.cleanup">cleanup() (whisper_live.server.ServeClient method)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.client.Client">Client (class in whisper_live.client)</a>
</li>
<li><a href="index.html#whisper_live.client.Client.close_websocket">close_websocket() (whisper_live.client.Client method)</a>
</li>
</ul></td>
</tr></table>
<h2 id="D">D</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.server.ServeClient.disconnect">disconnect() (whisper_live.server.ServeClient method)</a>
</li>
</ul></td>
</tr></table>
<h2 id="F">F</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.server.ServeClient.fill_output">fill_output() (whisper_live.server.ServeClient method)</a>
</li>
</ul></td>
</tr></table>
<h2 id="G">G</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.client.Client.get_client_socket">get_client_socket() (whisper_live.client.Client method)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.server.TranscriptionServer.get_wait_time">get_wait_time() (whisper_live.server.TranscriptionServer method)</a>
</li>
</ul></td>
</tr></table>
<h2 id="M">M</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li>
module
<ul>
<li><a href="index.html#module-whisper_live.client">whisper_live.client</a>
</li>
<li><a href="index.html#module-whisper_live.server">whisper_live.server</a>
</li>
</ul></li>
</ul></td>
</tr></table>
<h2 id="O">O</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.client.Client.on_message">on_message() (whisper_live.client.Client method)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.client.Client.on_open">on_open() (whisper_live.client.Client method)</a>
</li>
</ul></td>
</tr></table>
<h2 id="P">P</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.client.Client.play_file">play_file() (whisper_live.client.Client method)</a>
</li>
</ul></td>
</tr></table>
<h2 id="R">R</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.client.Client.record">record() (whisper_live.client.Client method)</a>
</li>
<li><a href="index.html#whisper_live.server.TranscriptionServer.recv_audio">recv_audio() (whisper_live.server.TranscriptionServer method)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.client.resample">resample() (in module whisper_live.client)</a>
</li>
<li><a href="index.html#whisper_live.server.TranscriptionServer.run">run() (whisper_live.server.TranscriptionServer method)</a>
</li>
</ul></td>
</tr></table>
<h2 id="S">S</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.client.Client.send_packet_to_server">send_packet_to_server() (whisper_live.client.Client method)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.server.ServeClient">ServeClient (class in whisper_live.server)</a>
</li>
<li><a href="index.html#whisper_live.server.ServeClient.speech_to_text">speech_to_text() (whisper_live.server.ServeClient method)</a>
</li>
</ul></td>
</tr></table>
<h2 id="T">T</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.client.TranscriptionClient">TranscriptionClient (class in whisper_live.client)</a>
</li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.server.TranscriptionServer">TranscriptionServer (class in whisper_live.server)</a>
</li>
</ul></td>
</tr></table>
<h2 id="U">U</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.server.ServeClient.update_segments">update_segments() (whisper_live.server.ServeClient method)</a>
</li>
</ul></td>
</tr></table>
<h2 id="W">W</h2>
<table style="width: 100%" class="indextable genindextable"><tr>
<td style="width: 33%; vertical-align: top;"><ul>
<li>
whisper_live.client
<ul>
<li><a href="index.html#module-whisper_live.client">module</a>
</li>
</ul></li>
<li>
whisper_live.server
<ul>
<li><a href="index.html#module-whisper_live.server">module</a>
</li>
</ul></li>
</ul></td>
<td style="width: 33%; vertical-align: top;"><ul>
<li><a href="index.html#whisper_live.client.Client.write_audio_frames_to_file">write_audio_frames_to_file() (whisper_live.client.Client method)</a>
</li>
<li><a href="index.html#whisper_live.client.Client.write_output_recording">write_output_recording() (whisper_live.client.Client method)</a>
</li>
</ul></td>
</tr></table>
</div>
</div>
</div>
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
<div class="sphinxsidebarwrapper">
<h1 class="logo"><a href="index.html">whisper_live</a></h1>
<h3>Navigation</h3>
<div class="relations">
<h3>Related Topics</h3>
<ul>
<li><a href="index.html">Documentation overview</a><ul>
</ul></li>
</ul>
</div>
<div id="searchbox" style="display: none" role="search">
<h3 id="searchlabel">Quick search</h3>
<div class="searchformwrapper">
<form class="search" action="search.html" method="get">
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
<input type="submit" value="Go" />
</form>
</div>
</div>
<script>document.getElementById('searchbox').style.display = "block"</script>
</div>
</div>
<div class="clearer"></div>
</div>
<div class="footer">
&copy;2023, Collabora.
|
Powered by <a href="http://sphinx-doc.org/">Sphinx 7.2.6</a>
&amp; <a href="https://github.com/bitprophet/alabaster">Alabaster 0.7.13</a>
</div>
</body>
</html>
+468
View File
@@ -0,0 +1,468 @@
<!DOCTYPE html>
<html lang="en" data-content_root="./">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Welcome to Whisper Live documentation! &#8212; whisper_live documentation</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=4f649999" />
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=039e1c02" />
<script src="_static/documentation_options.js?v=5929fcd5"></script>
<script src="_static/doctools.js?v=888ff710"></script>
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
<meta name="viewport" content="width=device-width, initial-scale=0.9, maximum-scale=0.9" />
</head><body>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<section id="welcome-to-whisper-live-documentation">
<h1>Welcome to Whisper Live documentation!<a class="headerlink" href="#welcome-to-whisper-live-documentation" title="Link to this heading"></a></h1>
<div class="toctree-wrapper compound">
</div>
<dl class="py class" id="module-whisper_live.server">
<dt class="sig sig-object py" id="whisper_live.server.ServeClient">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">whisper_live.server.</span></span><span class="sig-name descname"><span class="pre">ServeClient</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">websocket</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">task</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'transcribe'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">multilingual</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">language</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">client_uid</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.server.ServeClient" title="Link to this definition"></a></dt>
<dd><dl class="simple">
<dt>Attributes:</dt><dd><p>RATE (int): The audio sampling rate (constant) set to 16000.
SERVER_READY (str): A constant message indicating that the server is ready.
DISCONNECT (str): A constant message indicating that the client should disconnect.
client_uid (str): A unique identifier for the client.
data (bytes): Accumulated audio data.
frames (bytes): Accumulated audio frames.
language (str): The language for transcription.
task (str): The task type, e.g., “transcribe.”
transcriber (WhisperModel): The Whisper model for speech-to-text.
timestamp_offset (float): The offset in audio timestamps.
frames_np (numpy.ndarray): NumPy array to store audio frames.
frames_offset (float): The offset in audio frames.
text (list): List of transcribed text segments.
current_out (str): The current incomplete transcription.
prev_out (str): The previous incomplete transcription.
t_start (float): Timestamp for the start of transcription.
exit (bool): A flag to exit the transcription thread.
same_output_threshold (int): Threshold for consecutive same output segments.
show_prev_out_thresh (int): Threshold for showing previous output segments.
add_pause_thresh (int): Threshold for adding a pause (blank) segment.
transcript (list): List of transcribed segments.
send_last_n_segments (int): Number of last segments to send to the client.
wrapper (textwrap.TextWrapper): Text wrapper for formatting text.
pick_previous_segments (int): Number of previous segments to include in the output.
websocket: The WebSocket connection for the client.</p>
</dd>
</dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.server.ServeClient.add_frames">
<span class="sig-name descname"><span class="pre">add_frames</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">frame_np</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.server.ServeClient.add_frames" title="Link to this definition"></a></dt>
<dd><p>Add audio frames to the ongoing audio stream buffer.</p>
<p>This method is responsible for maintaining the audio stream buffer, allowing the continuous addition
of audio frames as they are received. It also ensures that the buffer does not exceed a specified size
to prevent excessive memory usage.</p>
<p>If the buffer size exceeds a threshold (45 seconds of audio data), it discards the oldest 30 seconds
of audio data to maintain a reasonable buffer size. If the buffer is empty, it initializes it with the provided
audio frame. The audio stream buffer is used for real-time processing of audio data for transcription.</p>
<dl class="simple">
<dt>Args:</dt><dd><p>frame_np (numpy.ndarray): The audio frame data as a NumPy array.</p>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.server.ServeClient.cleanup">
<span class="sig-name descname"><span class="pre">cleanup</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.server.ServeClient.cleanup" title="Link to this definition"></a></dt>
<dd><p>Perform cleanup tasks before exiting the transcription service.</p>
<p>This method performs necessary cleanup tasks, including stopping the transcription thread, marking
the exit flag to indicate the transcription thread should exit gracefully, and destroying resources
associated with the transcription process.</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.server.ServeClient.disconnect">
<span class="sig-name descname"><span class="pre">disconnect</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.server.ServeClient.disconnect" title="Link to this definition"></a></dt>
<dd><p>Notify the client of disconnection and send a disconnect message.</p>
<p>This method sends a disconnect message to the client via the WebSocket connection to notify them
that the transcription service is disconnecting gracefully.</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.server.ServeClient.fill_output">
<span class="sig-name descname"><span class="pre">fill_output</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">output</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.server.ServeClient.fill_output" title="Link to this definition"></a></dt>
<dd><p>Format the current incomplete transcription output by combining it with previous complete segments.
The resulting transcription is wrapped into two lines, each containing a maximum of 50 characters.</p>
<p>It ensures that the combined transcription fits within two lines, with a maximum of 50 characters per line.
Segments are concatenated in the order they exist in the list of previous segments, with the most
recent complete segment first and older segments prepended as needed to maintain the character limit.
If a 3-second pause is detected in the previous segments, any text preceding it is discarded to ensure
the transcription starts with the most recent complete content. The resulting transcription is returned
as a single string.</p>
<dl class="simple">
<dt>Args:</dt><dd><p>output(str): The current incomplete transcription segment.</p>
</dd>
<dt>Returns:</dt><dd><p>str: A formatted transcription wrapped in two lines.</p>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.server.ServeClient.speech_to_text">
<span class="sig-name descname"><span class="pre">speech_to_text</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.server.ServeClient.speech_to_text" title="Link to this definition"></a></dt>
<dd><p>Process an audio stream in an infinite loop, continuously transcribing the speech.</p>
<p>This method continuously receives audio frames, performs real-time transcription, and sends
transcribed segments to the client via a WebSocket connection.</p>
<p>If the clients language is not detected, it waits for 30 seconds of audio input to make a language prediction.
It utilizes the Whisper ASR model to transcribe the audio, continuously processing and streaming results. Segments
are sent to the client in real-time, and a history of segments is maintained to provide context.Pauses in speech
(no output from Whisper) are handled by showing the previous output for a set duration. A blank segment is added if
there is no speech for a specified duration to indicate a pause.</p>
<dl class="simple">
<dt>Raises:</dt><dd><p>Exception: If there is an issue with audio processing or WebSocket communication.</p>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.server.ServeClient.update_segments">
<span class="sig-name descname"><span class="pre">update_segments</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">segments</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">duration</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.server.ServeClient.update_segments" title="Link to this definition"></a></dt>
<dd><p>Processes the segments from whisper. Appends all the segments to the list
except for the last segment assuming that it is incomplete.</p>
<p>Updates the ongoing transcript with transcribed segments, including their start and end times.
Complete segments are appended to the transcript in chronological order. Incomplete segments
(assumed to be the last one) are processed to identify repeated content. If the same incomplete
segment is seen multiple times, it updates the offset and appends the segment to the transcript.
A threshold is used to detect repeated content and ensure it is only included once in the transcript.
The timestamp offset is updated based on the duration of processed segments. The method returns the
last processed segment, allowing it to be sent to the client for real-time updates.</p>
<dl class="simple">
<dt>Args:</dt><dd><p>segments(dict) : dictionary of segments as returned by whisper
duration(float): duration of the current chunk</p>
</dd>
<dt>Returns:</dt><dd><dl class="simple">
<dt>dict or None: The last processed segment with its start time, end time, and transcribed text.</dt><dd><p>Returns None if there are no valid segments to process.</p>
</dd>
</dl>
</dd>
</dl>
</dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="whisper_live.server.TranscriptionServer">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">whisper_live.server.</span></span><span class="sig-name descname"><span class="pre">TranscriptionServer</span></span><a class="headerlink" href="#whisper_live.server.TranscriptionServer" title="Link to this definition"></a></dt>
<dd><p>Represents a transcription server that handles incoming audio from clients.</p>
<dl class="simple">
<dt>Attributes:</dt><dd><p>RATE (int): The audio sampling rate (constant) set to 16000.
vad_model (torch.Module): The voice activity detection model.
vad_threshold (float): The voice activity detection threshold.
clients (dict): A dictionary to store connected clients.
websockets (dict): A dictionary to store WebSocket connections.
clients_start_time (dict): A dictionary to track client start times.
max_clients (int): Maximum allowed connected clients.
max_connection_time (int): Maximum allowed connection time in seconds.</p>
</dd>
</dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.server.TranscriptionServer.get_wait_time">
<span class="sig-name descname"><span class="pre">get_wait_time</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.server.TranscriptionServer.get_wait_time" title="Link to this definition"></a></dt>
<dd><p>Calculate and return the estimated wait time for clients.</p>
<dl class="simple">
<dt>Returns:</dt><dd><p>float: The estimated wait time in minutes.</p>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.server.TranscriptionServer.recv_audio">
<span class="sig-name descname"><span class="pre">recv_audio</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">websocket</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.server.TranscriptionServer.recv_audio" title="Link to this definition"></a></dt>
<dd><p>Receive audio chunks from a client in an infinite loop.</p>
<p>Continuously receives audio frames from a connected client
over a WebSocket connection. It processes the audio frames using a
voice activity detection (VAD) model to determine if they contain speech
or not. If the audio frame contains speech, it is added to the clients
audio data for ASR.
If the maximum number of clients is reached, the method sends a
“WAIT” status to the client, indicating that they should wait
until a slot is available.
If a clients connection exceeds the maximum allowed time, it will
be disconnected, and the clients resources will be cleaned up.</p>
<dl class="simple">
<dt>Args:</dt><dd><p>websocket (WebSocket): The WebSocket connection for the client.</p>
</dd>
<dt>Raises:</dt><dd><p>Exception: If there is an error during the audio frame processing.</p>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.server.TranscriptionServer.run">
<span class="sig-name descname"><span class="pre">run</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">host</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">port</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">9090</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.server.TranscriptionServer.run" title="Link to this definition"></a></dt>
<dd><p>Run the transcription server.</p>
<dl class="simple">
<dt>Args:</dt><dd><p>host (str): The host address to bind the server.
port (int): The port number to bind the server.</p>
</dd>
</dl>
</dd></dl>
</dd></dl>
<dl class="py class" id="module-whisper_live.client">
<dt class="sig sig-object py" id="whisper_live.client.Client">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">whisper_live.client.</span></span><span class="sig-name descname"><span class="pre">Client</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">host</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">port</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_multilingual</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lang</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">translate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.client.Client" title="Link to this definition"></a></dt>
<dd><p>Handles audio recording, streaming, and communication with a server using WebSocket.</p>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.client.Client.bytes_to_float_array">
<em class="property"><span class="pre">static</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">bytes_to_float_array</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">audio_bytes</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.client.Client.bytes_to_float_array" title="Link to this definition"></a></dt>
<dd><p>Convert audio data from bytes to a NumPy float array.</p>
<p>It assumes that the audio data is in 16-bit PCM format. The audio data is normalized to
have values between -1 and 1.</p>
<dl class="simple">
<dt>Args:</dt><dd><p>audio_bytes (bytes): Audio data in bytes.</p>
</dd>
<dt>Returns:</dt><dd><p>np.ndarray: A NumPy array containing the audio data as float values normalized between -1 and 1.</p>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.client.Client.close_websocket">
<span class="sig-name descname"><span class="pre">close_websocket</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.client.Client.close_websocket" title="Link to this definition"></a></dt>
<dd><p>Close the WebSocket connection and join the WebSocket thread.</p>
<p>First attempts to close the WebSocket connection using <cite>self.client_socket.close()</cite>. After
closing the connection, it joins the WebSocket thread to ensure proper termination.</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.client.Client.get_client_socket">
<span class="sig-name descname"><span class="pre">get_client_socket</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.client.Client.get_client_socket" title="Link to this definition"></a></dt>
<dd><p>Get the WebSocket client socket instance.</p>
<dl class="simple">
<dt>Returns:</dt><dd><p>WebSocketApp: The WebSocket client socket instance currently in use by the client.</p>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.client.Client.on_message">
<span class="sig-name descname"><span class="pre">on_message</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ws</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">message</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.client.Client.on_message" title="Link to this definition"></a></dt>
<dd><p>Callback function called when a message is received from the server.</p>
<p>It updates various attributes of the client based on the received message, including
recording status, language detection, and server messages. If a disconnect message
is received, it sets the recording status to False.</p>
<dl class="simple">
<dt>Args:</dt><dd><p>ws (websocket.WebSocketApp): The WebSocket client instance.
message (str): The received message from the server.</p>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.client.Client.on_open">
<span class="sig-name descname"><span class="pre">on_open</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">ws</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.client.Client.on_open" title="Link to this definition"></a></dt>
<dd><p>Callback function called when the WebSocket connection is successfully opened.</p>
<p>Sends an initial configuration message to the server, including client UID, multilingual mode,
language selection, and task type.</p>
<dl class="simple">
<dt>Args:</dt><dd><p>ws (websocket.WebSocketApp): The WebSocket client instance.</p>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.client.Client.play_file">
<span class="sig-name descname"><span class="pre">play_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">filename</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.client.Client.play_file" title="Link to this definition"></a></dt>
<dd><p>Play an audio file and send it to the server for processing.</p>
<p>Reads an audio file, plays it through the audio output, and simultaneously sends
the audio data to the server for processing. It uses PyAudio to create an audio
stream for playback. The audio data is read from the file in chunks, converted to
floating-point format, and sent to the server using WebSocket communication.
This method is typically used when you want to process pre-recorded audio and send it
to the server in real-time.</p>
<dl class="simple">
<dt>Args:</dt><dd><p>filename (str): The path to the audio file to be played and sent to the server.</p>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.client.Client.record">
<span class="sig-name descname"><span class="pre">record</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">out_file</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'output_recording.wav'</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.client.Client.record" title="Link to this definition"></a></dt>
<dd><p>Record audio data from the input stream and save it to a WAV file.</p>
<p>Continuously records audio data from the input stream, sends it to the server via a WebSocket
connection, and simultaneously saves it to multiple WAV files in chunks. It stops recording when
the <cite>RECORD_SECONDS</cite> duration is reached or when the <cite>RECORDING</cite> flag is set to <cite>False</cite>.</p>
<p>Audio data is saved in chunks to the “chunks” directory. Each chunk is saved as a separate WAV file.
The recording will continue until the specified duration is reached or until the <cite>RECORDING</cite> flag is set to <cite>False</cite>.
The recording process can be interrupted by sending a KeyboardInterrupt (e.g., pressing Ctrl+C). After recording,
the method combines all the saved audio chunks into the specified <cite>out_file</cite>.</p>
<dl class="simple">
<dt>Args:</dt><dd><p>out_file (str, optional): The name of the output WAV file to save the entire recording. Default is “output_recording.wav”.</p>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.client.Client.send_packet_to_server">
<span class="sig-name descname"><span class="pre">send_packet_to_server</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">message</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.client.Client.send_packet_to_server" title="Link to this definition"></a></dt>
<dd><p>Send an audio packet to the server using WebSocket.</p>
<dl class="simple">
<dt>Args:</dt><dd><p>message (bytes): The audio data packet in bytes to be sent to the server.</p>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.client.Client.write_audio_frames_to_file">
<span class="sig-name descname"><span class="pre">write_audio_frames_to_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">frames</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">file_name</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.client.Client.write_audio_frames_to_file" title="Link to this definition"></a></dt>
<dd><p>Write audio frames to a WAV file.</p>
<p>The WAV file is created or overwritten with the specified name. The audio frames should be
in the correct format and match the specified channel, sample width, and sample rate.</p>
<dl class="simple">
<dt>Args:</dt><dd><p>frames (bytes): The audio frames to be written to the file.
file_name (str): The name of the WAV file to which the frames will be written.</p>
</dd>
</dl>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="whisper_live.client.Client.write_output_recording">
<span class="sig-name descname"><span class="pre">write_output_recording</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">n_audio_file</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">out_file</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.client.Client.write_output_recording" title="Link to this definition"></a></dt>
<dd><p>Combine and save recorded audio chunks into a single WAV file.</p>
<p>The individual audio chunk files are expected to be located in the “chunks” directory. Reads each chunk
file, appends its audio data to the final recording, and then deletes the chunk file. After combining
and saving, the final recording is stored in the specified <cite>out_file</cite>.</p>
<dl class="simple">
<dt>Args:</dt><dd><p>n_audio_file (int): The number of audio chunk files to combine.
out_file (str): The name of the output WAV file to save the final recording.</p>
</dd>
</dl>
</dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="whisper_live.client.TranscriptionClient">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">whisper_live.client.</span></span><span class="sig-name descname"><span class="pre">TranscriptionClient</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">host</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">port</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">is_multilingual</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">lang</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">translate</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.client.TranscriptionClient" title="Link to this definition"></a></dt>
<dd><p>Client for handling audio transcription tasks via a WebSocket connection.</p>
<p>Acts as a high-level client for audio transcription tasks using a WebSocket connection. It can be used
to send audio data for transcription to a server and receive transcribed text segments.</p>
<dl class="simple">
<dt>Args:</dt><dd><p>host (str): The hostname or IP address of the server.
port (int): The port number to connect to on the server.
is_multilingual (bool, optional): Indicates whether the transcription should support multiple languages (default is False).
lang (str, optional): The primary language for transcription (used if <cite>is_multilingual</cite> is False). Default is None, which defaults to English (en).
translate (bool, optional): Indicates whether translation tasks are required (default is False).</p>
</dd>
<dt>Attributes:</dt><dd><p>client (Client): An instance of the underlying Client class responsible for handling the WebSocket connection.</p>
</dd>
<dt>Example:</dt><dd><p>To create a TranscriptionClient and start transcription on microphone audio:
<code class="docutils literal notranslate"><span class="pre">`python</span>
<span class="pre">transcription_client</span> <span class="pre">=</span> <span class="pre">TranscriptionClient(host=&quot;localhost&quot;,</span> <span class="pre">port=9090,</span> <span class="pre">is_multilingual=True)</span>
<span class="pre">transcription_client()</span>
<span class="pre">`</span></code></p>
</dd>
</dl>
</dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="whisper_live.client.resample">
<span class="sig-prename descclassname"><span class="pre">whisper_live.client.</span></span><span class="sig-name descname"><span class="pre">resample</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">file</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sr</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">16000</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#whisper_live.client.resample" title="Link to this definition"></a></dt>
<dd><p># <a class="reference external" href="https://github.com/openai/whisper/blob/7858aa9c08d98f75575035ecd6481f462d66ca27/whisper/audio.py#L22">https://github.com/openai/whisper/blob/7858aa9c08d98f75575035ecd6481f462d66ca27/whisper/audio.py#L22</a>
Open an audio file and read as mono waveform, resampling as necessary,
save the resampled audio</p>
<dl class="simple">
<dt>Args:</dt><dd><p>file (str): The audio file to open
sr (int): The sample rate to resample the audio if necessary</p>
</dd>
<dt>Returns:</dt><dd><p>resampled_file (str): The resampled audio file</p>
</dd>
</dl>
</dd></dl>
</section>
<section id="indices-and-tables">
<h1>Indices and tables<a class="headerlink" href="#indices-and-tables" title="Link to this heading"></a></h1>
<ul class="simple">
<li><p><a class="reference internal" href="genindex.html"><span class="std std-ref">Index</span></a></p></li>
<li><p><a class="reference internal" href="py-modindex.html"><span class="std std-ref">Module Index</span></a></p></li>
<li><p><a class="reference internal" href="search.html"><span class="std std-ref">Search Page</span></a></p></li>
</ul>
</section>
</div>
</div>
</div>
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
<div class="sphinxsidebarwrapper">
<h1 class="logo"><a href="#">whisper_live</a></h1>
<h3>Navigation</h3>
<div class="relations">
<h3>Related Topics</h3>
<ul>
<li><a href="#">Documentation overview</a><ul>
</ul></li>
</ul>
</div>
<div id="searchbox" style="display: none" role="search">
<h3 id="searchlabel">Quick search</h3>
<div class="searchformwrapper">
<form class="search" action="search.html" method="get">
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
<input type="submit" value="Go" />
</form>
</div>
</div>
<script>document.getElementById('searchbox').style.display = "block"</script>
</div>
</div>
<div class="clearer"></div>
</div>
<div class="footer">
&copy;2023, Collabora.
|
Powered by <a href="http://sphinx-doc.org/">Sphinx 7.2.6</a>
&amp; <a href="https://github.com/bitprophet/alabaster">Alabaster 0.7.13</a>
|
<a href="_sources/index.rst.txt"
rel="nofollow">Page source</a>
</div>
</body>
</html>
+5
View File
@@ -0,0 +1,5 @@
# Sphinx inventory version 2
# Project: whisper_live
# Version:
# The remainder of this file is compressed using zlib.
xÚ­UËnÂ0¼ç+\µ×Dåʵ§J­T‰J­Å^«ŽmùAÈßׯ@A hNIvwÆû˜uºF8ƒ–J±ÁŠIÊÓÏ[̓DòJ„⸭ßÊçl+_HYt—¨êífœ#³SìmPµê=:ê5]K
+123
View File
@@ -0,0 +1,123 @@
<!DOCTYPE html>
<html lang="en" data-content_root="./">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Python Module Index &#8212; whisper_live documentation</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=4f649999" />
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=039e1c02" />
<script src="_static/documentation_options.js?v=5929fcd5"></script>
<script src="_static/doctools.js?v=888ff710"></script>
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
<meta name="viewport" content="width=device-width, initial-scale=0.9, maximum-scale=0.9" />
</head><body>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<h1>Python Module Index</h1>
<div class="modindex-jumpbox">
<a href="#cap-w"><strong>w</strong></a>
</div>
<table class="indextable modindextable">
<tr class="pcap"><td></td><td>&#160;</td><td></td></tr>
<tr class="cap" id="cap-w"><td></td><td>
<strong>w</strong></td><td></td></tr>
<tr>
<td><img src="_static/minus.png" class="toggler"
id="toggle-1" style="display: none" alt="-" /></td>
<td>
<code class="xref">whisper_live</code></td><td>
<em></em></td></tr>
<tr class="cg-1">
<td></td>
<td>&#160;&#160;&#160;
<a href="index.html#module-whisper_live.client"><code class="xref">whisper_live.client</code></a></td><td>
<em></em></td></tr>
<tr class="cg-1">
<td></td>
<td>&#160;&#160;&#160;
<a href="index.html#module-whisper_live.server"><code class="xref">whisper_live.server</code></a></td><td>
<em></em></td></tr>
</table>
</div>
</div>
</div>
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
<div class="sphinxsidebarwrapper">
<h1 class="logo"><a href="index.html">whisper_live</a></h1>
<h3>Navigation</h3>
<div class="relations">
<h3>Related Topics</h3>
<ul>
<li><a href="index.html">Documentation overview</a><ul>
</ul></li>
</ul>
</div>
<div id="searchbox" style="display: none" role="search">
<h3 id="searchlabel">Quick search</h3>
<div class="searchformwrapper">
<form class="search" action="search.html" method="get">
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
<input type="submit" value="Go" />
</form>
</div>
</div>
<script>document.getElementById('searchbox').style.display = "block"</script>
</div>
</div>
<div class="clearer"></div>
</div>
<div class="footer">
&copy;2023, Collabora.
|
Powered by <a href="http://sphinx-doc.org/">Sphinx 7.2.6</a>
&amp; <a href="https://github.com/bitprophet/alabaster">Alabaster 0.7.13</a>
</div>
</body>
</html>
+117
View File
@@ -0,0 +1,117 @@
<!DOCTYPE html>
<html lang="en" data-content_root="./">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Search &#8212; whisper_live documentation</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=4f649999" />
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=039e1c02" />
<script src="_static/documentation_options.js?v=5929fcd5"></script>
<script src="_static/doctools.js?v=888ff710"></script>
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="_static/searchtools.js"></script>
<script src="_static/language_data.js"></script>
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="#" />
<script src="searchindex.js" defer></script>
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
<meta name="viewport" content="width=device-width, initial-scale=0.9, maximum-scale=0.9" />
</head><body>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<h1 id="search-documentation">Search</h1>
<noscript>
<div class="admonition warning">
<p>
Please activate JavaScript to enable the search
functionality.
</p>
</div>
</noscript>
<p>
Searching for multiple words only shows matches that contain
all words.
</p>
<form action="" method="get">
<input type="text" name="q" aria-labelledby="search-documentation" value="" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
<input type="submit" value="search" />
<span id="search-progress" style="padding-left: 10px"></span>
</form>
<div id="search-results">
</div>
</div>
</div>
</div>
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
<div class="sphinxsidebarwrapper">
<h1 class="logo"><a href="index.html">whisper_live</a></h1>
<h3>Navigation</h3>
<div class="relations">
<h3>Related Topics</h3>
<ul>
<li><a href="index.html">Documentation overview</a><ul>
</ul></li>
</ul>
</div>
</div>
</div>
<div class="clearer"></div>
</div>
<div class="footer">
&copy;2023, Collabora.
|
Powered by <a href="http://sphinx-doc.org/">Sphinx 7.2.6</a>
&amp; <a href="https://github.com/bitprophet/alabaster">Alabaster 0.7.13</a>
</div>
</body>
</html>
File diff suppressed because one or more lines are too long
+1
View File
@@ -0,0 +1 @@
<meta http-equiv="refresh" content="0; url=./html/index.html" />
+169 -13
View File
@@ -18,12 +18,13 @@ def resample(file: str, sr: int = 16000):
# https://github.com/openai/whisper/blob/7858aa9c08d98f75575035ecd6481f462d66ca27/whisper/audio.py#L22 # https://github.com/openai/whisper/blob/7858aa9c08d98f75575035ecd6481f462d66ca27/whisper/audio.py#L22
Open an audio file and read as mono waveform, resampling as necessary, Open an audio file and read as mono waveform, resampling as necessary,
save the resampled audio save the resampled audio
Parameters
---------- Args:
file: str file (str): The audio file to open
The audio file to open sr (int): The sample rate to resample the audio if necessary
sr: int
The sample rate to resample the audio if necessary Returns:
resampled_file (str): The resampled audio file
""" """
try: try:
# This launches a subprocess to decode audio while down-mixing and resampling as necessary. # This launches a subprocess to decode audio while down-mixing and resampling as necessary.
@@ -43,11 +44,28 @@ def resample(file: str, sr: int = 16000):
class Client: class Client:
"""
Handles audio recording, streaming, and communication with a server using WebSocket.
"""
INSTANCES = {} INSTANCES = {}
def __init__( def __init__(
self, host=None, port=None, is_multilingual=False, lang=None, translate=False self, host=None, port=None, is_multilingual=False, lang=None, translate=False
): ):
"""
Initializes a Client instance for audio recording and streaming to a server.
If host and port are not provided, the WebSocket connection will not be established.
When translate is True, the task will be set to "translate" instead of "transcribe".
he audio recording starts immediately upon initialization.
Args:
host (str): The hostname or IP address of the server.
port (int): The port number for the WebSocket server.
is_multilingual (bool, optional): Specifies if multilingual transcription is enabled. Default is False.
lang (str, optional): The selected language for transcription when multilingual is disabled. Default is None.
translate (bool, optional): Specifies if the task is translation. Default is False.
"""
self.chunk = 1024 self.chunk = 1024
self.format = pyaudio.paInt16 self.format = pyaudio.paInt16
self.channels = 1 self.channels = 1
@@ -77,7 +95,6 @@ class Client:
frames_per_buffer=self.chunk, frames_per_buffer=self.chunk,
) )
# create websocket connection
if host is not None and port is not None: if host is not None and port is not None:
socket_url = f"ws://{host}:{port}" socket_url = f"ws://{host}:{port}"
self.client_socket = websocket.WebSocketApp( self.client_socket = websocket.WebSocketApp(
@@ -104,6 +121,18 @@ class Client:
print("[INFO]: * recording") print("[INFO]: * recording")
def on_message(self, ws, message): def on_message(self, ws, message):
"""
Callback function called when a message is received from the server.
It updates various attributes of the client based on the received message, including
recording status, language detection, and server messages. If a disconnect message
is received, it sets the recording status to False.
Args:
ws (websocket.WebSocketApp): The WebSocket client instance.
message (str): The received message from the server.
"""
self.last_response_recieved = time.time() self.last_response_recieved = time.time()
message = json.loads(message) message = json.loads(message)
@@ -164,6 +193,16 @@ class Client:
print(f"[INFO]: Websocket connection closed: {close_status_code}: {close_msg}") print(f"[INFO]: Websocket connection closed: {close_status_code}: {close_msg}")
def on_open(self, ws): def on_open(self, ws):
"""
Callback function called when the WebSocket connection is successfully opened.
Sends an initial configuration message to the server, including client UID, multilingual mode,
language selection, and task type.
Args:
ws (websocket.WebSocketApp): The WebSocket client instance.
"""
print(self.multilingual, self.language, self.task) print(self.multilingual, self.language, self.task)
print("[INFO]: Opened connection") print("[INFO]: Opened connection")
@@ -180,16 +219,49 @@ class Client:
@staticmethod @staticmethod
def bytes_to_float_array(audio_bytes): def bytes_to_float_array(audio_bytes):
"""
Convert audio data from bytes to a NumPy float array.
It assumes that the audio data is in 16-bit PCM format. The audio data is normalized to
have values between -1 and 1.
Args:
audio_bytes (bytes): Audio data in bytes.
Returns:
np.ndarray: A NumPy array containing the audio data as float values normalized between -1 and 1.
"""
raw_data = np.frombuffer(buffer=audio_bytes, dtype=np.int16) raw_data = np.frombuffer(buffer=audio_bytes, dtype=np.int16)
return raw_data.astype(np.float32) / 32768.0 return raw_data.astype(np.float32) / 32768.0
def send_packet_to_server(self, message): def send_packet_to_server(self, message):
"""
Send an audio packet to the server using WebSocket.
Args:
message (bytes): The audio data packet in bytes to be sent to the server.
"""
try: try:
self.client_socket.send(message, websocket.ABNF.OPCODE_BINARY) self.client_socket.send(message, websocket.ABNF.OPCODE_BINARY)
except Exception as e: except Exception as e:
print(e) print(e)
def play_file(self, filename): def play_file(self, filename):
"""
Play an audio file and send it to the server for processing.
Reads an audio file, plays it through the audio output, and simultaneously sends
the audio data to the server for processing. It uses PyAudio to create an audio
stream for playback. The audio data is read from the file in chunks, converted to
floating-point format, and sent to the server using WebSocket communication.
This method is typically used when you want to process pre-recorded audio and send it
to the server in real-time.
Args:
filename (str): The path to the audio file to be played and sent to the server.
"""
# read audio and create pyaudio stream # read audio and create pyaudio stream
with wave.open(filename, "rb") as wavfile: with wave.open(filename, "rb") as wavfile:
self.stream = self.p.open( self.stream = self.p.open(
@@ -213,8 +285,7 @@ class Client:
wavfile.close() wavfile.close()
assert self.last_response_recieved assert self.last_response_recieved
elapsed_time = time.time() - self.last_response_recieved while time.time() - self.last_response_recieved < self.disconnect_if_no_response_for:
while elapsed_time < self.disconnect_if_no_response_for:
continue continue
self.stream.close() self.stream.close()
self.close_websocket() self.close_websocket()
@@ -228,20 +299,44 @@ class Client:
print("[INFO]: Keyboard interrupt.") print("[INFO]: Keyboard interrupt.")
def close_websocket(self): def close_websocket(self):
"""
Close the WebSocket connection and join the WebSocket thread.
First attempts to close the WebSocket connection using `self.client_socket.close()`. After
closing the connection, it joins the WebSocket thread to ensure proper termination.
"""
try: try:
self.client_socket.close() # Close the WebSocket connection self.client_socket.close()
except Exception as e: except Exception as e:
print("[ERROR]: Error closing WebSocket:", e) print("[ERROR]: Error closing WebSocket:", e)
try: try:
self.ws_thread.join() # Wait for the WebSocket thread to finish self.ws_thread.join()
except Exception as e: except Exception as e:
print("[ERROR:] Error joining WebSocket thread:", e) print("[ERROR:] Error joining WebSocket thread:", e)
def get_client_socket(self): def get_client_socket(self):
"""
Get the WebSocket client socket instance.
Returns:
WebSocketApp: The WebSocket client socket instance currently in use by the client.
"""
return self.client_socket return self.client_socket
def write_audio_frames_to_file(self, frames, file_name): def write_audio_frames_to_file(self, frames, file_name):
"""
Write audio frames to a WAV file.
The WAV file is created or overwritten with the specified name. The audio frames should be
in the correct format and match the specified channel, sample width, and sample rate.
Args:
frames (bytes): The audio frames to be written to the file.
file_name (str): The name of the WAV file to which the frames will be written.
"""
with wave.open(file_name, "wb") as wavfile: with wave.open(file_name, "wb") as wavfile:
wavfile: wave.Wave_write wavfile: wave.Wave_write
wavfile.setnchannels(self.channels) wavfile.setnchannels(self.channels)
@@ -250,8 +345,23 @@ class Client:
wavfile.writeframes(frames) wavfile.writeframes(frames)
def record(self, out_file="output_recording.wav"): def record(self, out_file="output_recording.wav"):
"""
Record audio data from the input stream and save it to a WAV file.
Continuously records audio data from the input stream, sends it to the server via a WebSocket
connection, and simultaneously saves it to multiple WAV files in chunks. It stops recording when
the `RECORD_SECONDS` duration is reached or when the `RECORDING` flag is set to `False`.
Audio data is saved in chunks to the "chunks" directory. Each chunk is saved as a separate WAV file.
The recording will continue until the specified duration is reached or until the `RECORDING` flag is set to `False`.
The recording process can be interrupted by sending a KeyboardInterrupt (e.g., pressing Ctrl+C). After recording,
the method combines all the saved audio chunks into the specified `out_file`.
Args:
out_file (str, optional): The name of the output WAV file to save the entire recording. Default is "output_recording.wav".
"""
n_audio_file = 0 n_audio_file = 0
# create dir for saving audio chunks
if not os.path.exists("chunks"): if not os.path.exists("chunks"):
os.makedirs("chunks", exist_ok=True) os.makedirs("chunks", exist_ok=True)
try: try:
@@ -289,10 +399,22 @@ class Client:
self.p.terminate() self.p.terminate()
self.close_websocket() self.close_websocket()
# combine all the audio files
self.write_output_recording(n_audio_file, out_file) self.write_output_recording(n_audio_file, out_file)
def write_output_recording(self, n_audio_file, out_file): def write_output_recording(self, n_audio_file, out_file):
"""
Combine and save recorded audio chunks into a single WAV file.
The individual audio chunk files are expected to be located in the "chunks" directory. Reads each chunk
file, appends its audio data to the final recording, and then deletes the chunk file. After combining
and saving, the final recording is stored in the specified `out_file`.
Args:
n_audio_file (int): The number of audio chunk files to combine.
out_file (str): The name of the output WAV file to save the final recording.
"""
input_files = [ input_files = [
f"chunks/{i}.wav" f"chunks/{i}.wav"
for i in range(n_audio_file) for i in range(n_audio_file)
@@ -316,10 +438,44 @@ class Client:
class TranscriptionClient: class TranscriptionClient:
"""
Client for handling audio transcription tasks via a WebSocket connection.
Acts as a high-level client for audio transcription tasks using a WebSocket connection. It can be used
to send audio data for transcription to a server and receive transcribed text segments.
Args:
host (str): The hostname or IP address of the server.
port (int): The port number to connect to on the server.
is_multilingual (bool, optional): Indicates whether the transcription should support multiple languages (default is False).
lang (str, optional): The primary language for transcription (used if `is_multilingual` is False). Default is None, which defaults to English ('en').
translate (bool, optional): Indicates whether translation tasks are required (default is False).
Attributes:
client (Client): An instance of the underlying Client class responsible for handling the WebSocket connection.
Example:
To create a TranscriptionClient and start transcription on microphone audio:
```python
transcription_client = TranscriptionClient(host="localhost", port=9090, is_multilingual=True)
transcription_client()
```
"""
def __init__(self, host, port, is_multilingual=False, lang=None, translate=False): def __init__(self, host, port, is_multilingual=False, lang=None, translate=False):
self.client = Client(host, port, is_multilingual, lang, translate) self.client = Client(host, port, is_multilingual, lang, translate)
def __call__(self, audio=None): def __call__(self, audio=None):
"""
Start the transcription process.
Initiates the transcription process by connecting to the server via a WebSocket. It waits for the server
to be ready to receive audio data and then sends audio for transcription. If an audio file is provided, it
will be played and streamed to the server; otherwise, it will perform live recording.
Args:
audio (str, optional): Path to an audio file for transcription. Default is None, which triggers live recording.
"""
print("[INFO]: Waiting for server ready ...") print("[INFO]: Waiting for server ready ...")
while not self.client.recording: while not self.client.recording:
if self.client.waiting: if self.client.waiting:
+149 -21
View File
@@ -1,16 +1,12 @@
import websockets import websockets
import pickle, struct, time, pyaudio import time
import threading import threading
import os, json import json
import base64
import wave
import textwrap import textwrap
import logging import logging
# logging.basicConfig(level = logging.INFO) # logging.basicConfig(level = logging.INFO)
from collections import deque
from dataclasses import dataclass
from websockets.sync.server import serve from websockets.sync.server import serve
import torch import torch
@@ -25,35 +21,66 @@ class TranscriptionServer:
Represents a transcription server that handles incoming audio from clients. Represents a transcription server that handles incoming audio from clients.
Attributes: Attributes:
RATE (int): The audio sampling rate (constant) set to 16000.
vad_model (torch.Module): The voice activity detection model.
vad_threshold (float): The voice activity detection threshold.
clients (dict): A dictionary to store connected clients. clients (dict): A dictionary to store connected clients.
websockets (dict): A dictionary to store WebSocket connections.
clients_start_time (dict): A dictionary to track client start times.
max_clients (int): Maximum allowed connected clients.
max_connection_time (int): Maximum allowed connection time in seconds.
""" """
RATE = 16000 RATE = 16000
def __init__(self): def __init__(self):
# voice activity detection model # voice activity detection model
self.vad_model = VoiceActivityDetection() self.vad_model = VoiceActivityDetection()
self.vad_threshold = 0.4 self.vad_threshold = 0.4
self.clients = {} self.clients = {}
self.websockets = {} self.websockets = {}
self.clients_start_time = {} self.clients_start_time = {}
self.max_clients = 4 self.max_clients = 4
self.max_connection_time = 600 # in seconds self.max_connection_time = 600
def get_wait_time(self): def get_wait_time(self):
"""
Calculate and return the estimated wait time for clients.
Returns:
float: The estimated wait time in minutes.
"""
wait_time = None wait_time = None
for k,v in self.clients_start_time.items():
for k, v in self.clients_start_time.items():
current_client_time_remaining = self.max_connection_time - (time.time() - v) current_client_time_remaining = self.max_connection_time - (time.time() - v)
if wait_time is None:
if wait_time is None or current_client_time_remaining < wait_time:
wait_time = current_client_time_remaining wait_time = current_client_time_remaining
elif current_client_time_remaining < wait_time:
wait_time = current_client_time_remaining return wait_time / 60
return wait_time/60
def recv_audio(self, websocket): def recv_audio(self, websocket):
""" """
Receive audio chunks from a client in an infinite loop. Receive audio chunks from a client in an infinite loop.
Continuously receives audio frames from a connected client
over a WebSocket connection. It processes the audio frames using a
voice activity detection (VAD) model to determine if they contain speech
or not. If the audio frame contains speech, it is added to the client's
audio data for ASR.
If the maximum number of clients is reached, the method sends a
"WAIT" status to the client, indicating that they should wait
until a slot is available.
If a client's connection exceeds the maximum allowed time, it will
be disconnected, and the client's resources will be cleaned up.
Args: Args:
websocket (WebSocket): The WebSocket connection for the client. websocket (WebSocket): The WebSocket connection for the client.
Raises:
Exception: If there is an error during the audio frame processing.
""" """
logging.info("New client connected") logging.info("New client connected")
options = websocket.recv() options = websocket.recv()
@@ -63,7 +90,7 @@ class TranscriptionServer:
logging.warning("Client Queue Full. Asking client to wait ...") logging.warning("Client Queue Full. Asking client to wait ...")
wait_time = self.get_wait_time() wait_time = self.get_wait_time()
response = { response = {
"uid" : options["uid"], "uid": options["uid"],
"status": "WAIT", "status": "WAIT",
"message": wait_time, "message": wait_time,
} }
@@ -96,6 +123,7 @@ class TranscriptionServer:
except Exception as e: except Exception as e:
logging.error(e) logging.error(e)
return return
self.clients[websocket].add_frames(frame_np) self.clients[websocket].add_frames(frame_np)
elapsed_time = time.time() - self.clients_start_time[websocket] elapsed_time = time.time() - self.clients_start_time[websocket]
@@ -109,7 +137,6 @@ class TranscriptionServer:
del websocket del websocket
break break
except Exception as e: except Exception as e:
logging.error(e) logging.error(e)
self.clients[websocket].cleanup() self.clients[websocket].cleanup()
@@ -117,7 +144,6 @@ class TranscriptionServer:
self.clients_start_time.pop(websocket) self.clients_start_time.pop(websocket)
logging.info("Connection Closed.") logging.info("Connection Closed.")
logging.info(self.clients) logging.info(self.clients)
del websocket del websocket
break break
@@ -134,11 +160,54 @@ class TranscriptionServer:
class ServeClient: class ServeClient:
"""
Attributes:
RATE (int): The audio sampling rate (constant) set to 16000.
SERVER_READY (str): A constant message indicating that the server is ready.
DISCONNECT (str): A constant message indicating that the client should disconnect.
client_uid (str): A unique identifier for the client.
data (bytes): Accumulated audio data.
frames (bytes): Accumulated audio frames.
language (str): The language for transcription.
task (str): The task type, e.g., "transcribe."
transcriber (WhisperModel): The Whisper model for speech-to-text.
timestamp_offset (float): The offset in audio timestamps.
frames_np (numpy.ndarray): NumPy array to store audio frames.
frames_offset (float): The offset in audio frames.
text (list): List of transcribed text segments.
current_out (str): The current incomplete transcription.
prev_out (str): The previous incomplete transcription.
t_start (float): Timestamp for the start of transcription.
exit (bool): A flag to exit the transcription thread.
same_output_threshold (int): Threshold for consecutive same output segments.
show_prev_out_thresh (int): Threshold for showing previous output segments.
add_pause_thresh (int): Threshold for adding a pause (blank) segment.
transcript (list): List of transcribed segments.
send_last_n_segments (int): Number of last segments to send to the client.
wrapper (textwrap.TextWrapper): Text wrapper for formatting text.
pick_previous_segments (int): Number of previous segments to include in the output.
websocket: The WebSocket connection for the client.
"""
RATE = 16000 RATE = 16000
SERVER_READY = "SERVER_READY" SERVER_READY = "SERVER_READY"
DISCONNECT = "DISCONNECT" DISCONNECT = "DISCONNECT"
def __init__(self, websocket, task="transcribe", device=None, multilingual=False, language=None, client_uid=None): def __init__(self, websocket, task="transcribe", device=None, multilingual=False, language=None, client_uid=None):
"""
Initialize a ServeClient instance.
The Whisper model is initialized based on the client's language and device availability.
The transcription thread is started upon initialization. A "SERVER_READY" message is sent
to the client to indicate that the server is ready.
Args:
websocket (WebSocket): The WebSocket connection for the client.
task (str, optional): The task type, e.g., "transcribe." Defaults to "transcribe".
device (str, optional): The device type for Whisper, "cuda" or "cpu". Defaults to None.
multilingual (bool, optional): Whether the client supports multilingual transcription. Defaults to False.
language (str, optional): The language for transcription. Defaults to None.
client_uid (str, optional): A unique identifier for the client. Defaults to None.
"""
self.client_uid = client_uid self.client_uid = client_uid
self.data = b"" self.data = b""
self.frames = b"" self.frames = b""
@@ -185,14 +254,21 @@ class ServeClient:
def fill_output(self, output): def fill_output(self, output):
""" """
Format output with current and previous complete segments Format the current incomplete transcription output by combining it with previous complete segments.
into two lines of 50 characters. The resulting transcription is wrapped into two lines, each containing a maximum of 50 characters.
It ensures that the combined transcription fits within two lines, with a maximum of 50 characters per line.
Segments are concatenated in the order they exist in the list of previous segments, with the most
recent complete segment first and older segments prepended as needed to maintain the character limit.
If a 3-second pause is detected in the previous segments, any text preceding it is discarded to ensure
the transcription starts with the most recent complete content. The resulting transcription is returned
as a single string.
Args: Args:
output(str): current incomplete segment output(str): The current incomplete transcription segment.
Returns: Returns:
transcription wrapped in two lines str: A formatted transcription wrapped in two lines.
""" """
text = '' text = ''
pick_prev = min(len(self.text), self.pick_previous_segments) pick_prev = min(len(self.text), self.pick_previous_segments)
@@ -206,6 +282,21 @@ class ServeClient:
return wrapped return wrapped
def add_frames(self, frame_np): def add_frames(self, frame_np):
"""
Add audio frames to the ongoing audio stream buffer.
This method is responsible for maintaining the audio stream buffer, allowing the continuous addition
of audio frames as they are received. It also ensures that the buffer does not exceed a specified size
to prevent excessive memory usage.
If the buffer size exceeds a threshold (45 seconds of audio data), it discards the oldest 30 seconds
of audio data to maintain a reasonable buffer size. If the buffer is empty, it initializes it with the provided
audio frame. The audio stream buffer is used for real-time processing of audio data for transcription.
Args:
frame_np (numpy.ndarray): The audio frame data as a NumPy array.
"""
if self.frames_np is not None and self.frames_np.shape[0] > 45*self.RATE: if self.frames_np is not None and self.frames_np.shape[0] > 45*self.RATE:
self.frames_offset += 30.0 self.frames_offset += 30.0
self.frames_np = self.frames_np[int(30*self.RATE):] self.frames_np = self.frames_np[int(30*self.RATE):]
@@ -216,7 +307,20 @@ class ServeClient:
def speech_to_text(self): def speech_to_text(self):
""" """
Process audio stream in an infinite loop. Process an audio stream in an infinite loop, continuously transcribing the speech.
This method continuously receives audio frames, performs real-time transcription, and sends
transcribed segments to the client via a WebSocket connection.
If the client's language is not detected, it waits for 30 seconds of audio input to make a language prediction.
It utilizes the Whisper ASR model to transcribe the audio, continuously processing and streaming results. Segments
are sent to the client in real-time, and a history of segments is maintained to provide context.Pauses in speech
(no output from Whisper) are handled by showing the previous output for a set duration. A blank segment is added if
there is no speech for a specified duration to indicate a pause.
Raises:
Exception: If there is an issue with audio processing or WebSocket communication.
""" """
# detect language # detect language
if self.language is None: if self.language is None:
@@ -324,12 +428,21 @@ class ServeClient:
Processes the segments from whisper. Appends all the segments to the list Processes the segments from whisper. Appends all the segments to the list
except for the last segment assuming that it is incomplete. except for the last segment assuming that it is incomplete.
Updates the ongoing transcript with transcribed segments, including their start and end times.
Complete segments are appended to the transcript in chronological order. Incomplete segments
(assumed to be the last one) are processed to identify repeated content. If the same incomplete
segment is seen multiple times, it updates the offset and appends the segment to the transcript.
A threshold is used to detect repeated content and ensure it is only included once in the transcript.
The timestamp offset is updated based on the duration of processed segments. The method returns the
last processed segment, allowing it to be sent to the client for real-time updates.
Args: Args:
segments(dict) : dictionary of segments as returned by whisper segments(dict) : dictionary of segments as returned by whisper
duration(float): duration of the current chunk duration(float): duration of the current chunk
Returns: Returns:
transcription for the current chunk dict or None: The last processed segment with its start time, end time, and transcribed text.
Returns None if there are no valid segments to process.
""" """
offset = None offset = None
self.current_out = '' self.current_out = ''
@@ -388,6 +501,13 @@ class ServeClient:
return last_segment return last_segment
def disconnect(self): def disconnect(self):
"""
Notify the client of disconnection and send a disconnect message.
This method sends a disconnect message to the client via the WebSocket connection to notify them
that the transcription service is disconnecting gracefully.
"""
self.websocket.send( self.websocket.send(
json.dumps( json.dumps(
{ {
@@ -398,6 +518,14 @@ class ServeClient:
) )
def cleanup(self): def cleanup(self):
"""
Perform cleanup tasks before exiting the transcription service.
This method performs necessary cleanup tasks, including stopping the transcription thread, marking
the exit flag to indicate the transcription thread should exit gracefully, and destroying resources
associated with the transcription process.
"""
logging.info("Cleaning up.") logging.info("Cleaning up.")
self.exit = True self.exit = True
self.transcriber.destroy() self.transcriber.destroy()