add nojekyll to resolve theme
This commit is contained in:
makaveli10
@@ -1,20 +0,0 @@
|
||||
# Minimal makefile for Sphinx documentation
|
||||
#
|
||||
|
||||
# You can set these variables from the command line, and also
|
||||
# from the environment for the first two.
|
||||
SPHINXOPTS ?=
|
||||
SPHINXBUILD ?= sphinx-build
|
||||
SOURCEDIR = source
|
||||
BUILDDIR = build
|
||||
|
||||
# Put it first so that "make" without argument is like "make help".
|
||||
help:
|
||||
@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
|
||||
|
||||
.PHONY: help Makefile
|
||||
|
||||
# Catch-all target: route all unknown targets to Sphinx using the new
|
||||
# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS).
|
||||
%: Makefile
|
||||
@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
|
||||
Binary file not shown.
Binary file not shown.
@@ -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
|
||||
|
Before Width: | Height: | Size: 286 B After Width: | Height: | Size: 286 B |
|
Before Width: | Height: | Size: 90 B After Width: | Height: | Size: 90 B |
|
Before Width: | Height: | Size: 90 B After Width: | Height: | Size: 90 B |
@@ -0,0 +1,295 @@
|
||||
<!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’s documentation! — 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-s-documentation">
|
||||
<h1>Welcome to whisper_live’s documentation!<a class="headerlink" href="#welcome-to-whisper-live-s-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 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.</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 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.</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>
|
||||
|
||||
</section>
|
||||
<section id="indices-and-tables">
|
||||
<span id="module-whisper_live.client"></span><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">
|
||||
©2023, Collabora.
|
||||
|
||||
|
|
||||
Powered by <a href="http://sphinx-doc.org/">Sphinx 7.2.6</a>
|
||||
& <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>
|
||||
+1
-295
@@ -1,295 +1 @@
|
||||
<!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’s documentation! — 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-s-documentation">
|
||||
<h1>Welcome to whisper_live’s documentation!<a class="headerlink" href="#welcome-to-whisper-live-s-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 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.</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 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.</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>
|
||||
|
||||
</section>
|
||||
<section id="indices-and-tables">
|
||||
<span id="module-whisper_live.client"></span><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">
|
||||
©2023, Collabora.
|
||||
|
||||
|
|
||||
Powered by <a href="http://sphinx-doc.org/">Sphinx 7.2.6</a>
|
||||
& <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>
|
||||
<meta http-equiv="refresh" content="0; url=./html/index.html" />
|
||||
@@ -1,35 +0,0 @@
|
||||
@ECHO OFF
|
||||
|
||||
pushd %~dp0
|
||||
|
||||
REM Command file for Sphinx documentation
|
||||
|
||||
if "%SPHINXBUILD%" == "" (
|
||||
set SPHINXBUILD=sphinx-build
|
||||
)
|
||||
set SOURCEDIR=source
|
||||
set BUILDDIR=build
|
||||
|
||||
%SPHINXBUILD% >NUL 2>NUL
|
||||
if errorlevel 9009 (
|
||||
echo.
|
||||
echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
|
||||
echo.installed, then set the SPHINXBUILD environment variable to point
|
||||
echo.to the full path of the 'sphinx-build' executable. Alternatively you
|
||||
echo.may add the Sphinx directory to PATH.
|
||||
echo.
|
||||
echo.If you don't have Sphinx installed, grab it from
|
||||
echo.https://www.sphinx-doc.org/
|
||||
exit /b 1
|
||||
)
|
||||
|
||||
if "%1" == "" goto help
|
||||
|
||||
%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
|
||||
goto end
|
||||
|
||||
:help
|
||||
%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
|
||||
|
||||
:end
|
||||
popd
|
||||
@@ -1,36 +0,0 @@
|
||||
# Configuration file for the Sphinx documentation builder.
|
||||
#
|
||||
# For the full list of built-in configuration values, see the documentation:
|
||||
# https://www.sphinx-doc.org/en/master/usage/configuration.html
|
||||
|
||||
# -- Project information -----------------------------------------------------
|
||||
# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
|
||||
import os
|
||||
import sys
|
||||
sys.path.insert(0, os.path.abspath('../..'))
|
||||
|
||||
project = 'whisper_live'
|
||||
copyright = '2023, Collabora'
|
||||
author = 'Collabora'
|
||||
|
||||
# -- General configuration ---------------------------------------------------
|
||||
# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
|
||||
|
||||
extensions = []
|
||||
|
||||
templates_path = ['_templates']
|
||||
exclude_patterns = []
|
||||
|
||||
|
||||
|
||||
# -- Options for HTML output -------------------------------------------------
|
||||
# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
|
||||
|
||||
html_theme = 'alabaster'
|
||||
html_static_path = ['_static']
|
||||
|
||||
extensions = [
|
||||
'sphinx.ext.duration',
|
||||
'sphinx.ext.doctest',
|
||||
'sphinx.ext.autodoc',
|
||||
]
|
||||
@@ -1,25 +0,0 @@
|
||||
.. 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's documentation!
|
||||
========================================
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 2
|
||||
|
||||
|
||||
.. automodule:: whisper_live.server
|
||||
:members:
|
||||
|
||||
.. automodule:: whisper_live.client
|
||||
|
||||
|
||||
|
||||
Indices and tables
|
||||
==================
|
||||
|
||||
* :ref:`genindex`
|
||||
* :ref:`modindex`
|
||||
* :ref:`search`
|
||||
Reference in New Issue
Block a user