From 7aad2ae72107f77b17b8d17d94763eb2f0a6e722 Mon Sep 17 00:00:00 2001 From: Sasa Trivic Date: Sun, 4 Feb 2024 17:35:20 +0100 Subject: [PATCH 1/3] Remove multilingual from Firefox. Sort languages, disable all inputs when capturing. Move both transcripts to the bottom center. --- Audio-Transcription-Chrome/content.js | 2 +- Audio-Transcription-Chrome/popup.js | 1 + Audio-Transcription-Firefox/content.js | 6 +- Audio-Transcription-Firefox/popup.html | 204 ++++++++++++------------- Audio-Transcription-Firefox/popup.js | 26 +--- Audio-Transcription-Firefox/style.css | 2 +- 6 files changed, 108 insertions(+), 133 deletions(-) diff --git a/Audio-Transcription-Chrome/content.js b/Audio-Transcription-Chrome/content.js index 3c911e4..c22376b 100644 --- a/Audio-Transcription-Chrome/content.js +++ b/Audio-Transcription-Chrome/content.js @@ -59,7 +59,7 @@ function init_element() { elem_container = document.createElement('div'); elem_container.id = "transcription"; - elem_container.style.cssText = 'padding-top:16px;font-size:18px;position: fixed; top: 50%; left: 50%; transform: translate(-50%, -50%);z-index: 9999;line-height:18px;width:500px;height:90px;opacity:0.9;z-index:100;background:black;border-radius:10px;color:white;'; + elem_container.style.cssText = 'padding-top:16px;font-size:18px;position: fixed; top: 85%; left: 50%; transform: translate(-50%, -50%);line-height:18px;width:500px;height:90px;opacity:0.9;z-index:100;background:black;border-radius:10px;color:white;'; for (var i = 0; i < 4; i++) { elem_text = document.createElement('span'); diff --git a/Audio-Transcription-Chrome/popup.js b/Audio-Transcription-Chrome/popup.js index 3c40aa8..57ae739 100644 --- a/Audio-Transcription-Chrome/popup.js +++ b/Audio-Transcription-Chrome/popup.js @@ -120,6 +120,7 @@ document.addEventListener("DOMContentLoaded", function () { stopButton.disabled = !isCapturing; useServerCheckbox.disabled = isCapturing; modelSizeDropdown.disabled = isCapturing; + languageDropdown.disabled = isCapturing; taskDropdown.disabled = isCapturing; startButton.classList.toggle("disabled", isCapturing); stopButton.classList.toggle("disabled", !isCapturing); diff --git a/Audio-Transcription-Firefox/content.js b/Audio-Transcription-Firefox/content.js index 82b045b..69611b5 100644 --- a/Audio-Transcription-Firefox/content.js +++ b/Audio-Transcription-Firefox/content.js @@ -66,16 +66,12 @@ function resampleTo16kHZ(audioData, origSampleRate = 44100) { function startRecording(data) { socket = new WebSocket(`ws://${data.host}:${data.port}/`); language = data.language; - if (language === null && !data.useMultilingual) { - language = 'en'; - } const uuid = generateUUID(); socket.onopen = function(e) { socket.send( JSON.stringify({ uid: uuid, - multilingual: data.useMultilingual, language: data.language, task: data.task, model: data.modelSize @@ -201,7 +197,7 @@ function init_element() { elem_container = document.createElement('div'); elem_container.id = "transcription"; - elem_container.style.cssText = 'padding-top:16px;font-size:18px;line-height:18px;top:0px;position:absolute;width:500px;height:90px;opacity:0.9;z-index:100;background:black;border-radius:10px;color:white;'; + elem_container.style.cssText = 'padding-top:16px;font-size:18px;line-height:18px;position:fixed;top:85%;left:50%;transform:translate(-50%,-50%);width:500px;height:90px;opacity:0.9;z-index:100;background:black;border-radius:10px;color:white;'; for (var i = 0; i < 4; i++) { elem_text = document.createElement('span'); diff --git a/Audio-Transcription-Firefox/popup.html b/Audio-Transcription-Firefox/popup.html index 30184a5..43b93a1 100644 --- a/Audio-Transcription-Firefox/popup.html +++ b/Audio-Transcription-Firefox/popup.html @@ -16,113 +16,109 @@ - -
- - -
- + - - - - - - + - - - - - - - - - - - - - - - + + - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
@@ -136,14 +132,18 @@
- \ No newline at end of file + diff --git a/Audio-Transcription-Firefox/popup.js b/Audio-Transcription-Firefox/popup.js index 17f8950..d71dc0a 100644 --- a/Audio-Transcription-Firefox/popup.js +++ b/Audio-Transcription-Firefox/popup.js @@ -3,7 +3,6 @@ document.addEventListener("DOMContentLoaded", function() { const stopButton = document.getElementById("stopCapture"); const useServerCheckbox = document.getElementById("useServerCheckbox"); - const useMultilingualCheckbox = document.getElementById('useMultilingualCheckbox'); const languageDropdown = document.getElementById('languageDropdown'); const taskDropdown = document.getElementById('taskDropdown'); const modelSizeDropdown = document.getElementById('modelSizeDropdown'); @@ -35,14 +34,6 @@ document.addEventListener("DOMContentLoaded", function() { } }); - browser.storage.local.get("useMultilingualModelState", ({ useMultilingualModelState }) => { - if (useMultilingualModelState !== undefined) { - useMultilingualCheckbox.checked = useMultilingualModelState; - languageDropdown.disabled = !useMultilingualModelState; - taskDropdown.disabled = !useMultilingualModelState; - } - }); - browser.storage.local.get("selectedLanguage", ({ selectedLanguage: storedLanguage }) => { if (storedLanguage !== undefined) { languageDropdown.value = storedLanguage; @@ -83,7 +74,6 @@ document.addEventListener("DOMContentLoaded", function() { data: { host: host, port: port, - useMultilingual: useMultilingualCheckbox.checked, language: selectedLanguage, task: selectedTask, modelSize: selectedModelSize @@ -125,9 +115,9 @@ document.addEventListener("DOMContentLoaded", function() { startButton.disabled = isCapturing; stopButton.disabled = !isCapturing; useServerCheckbox.disabled = isCapturing; - useMultilingualCheckbox.disabled = isCapturing; modelSizeDropdown.disabled = isCapturing; - + languageDropdown.disabled = isCapturing; + taskDropdown.disabled = isCapturing; startButton.classList.toggle("disabled", isCapturing); stopButton.classList.toggle("disabled", !isCapturing); } @@ -138,18 +128,6 @@ document.addEventListener("DOMContentLoaded", function() { browser.storage.local.set({ useServerState }); }); - useMultilingualCheckbox.addEventListener('change', function() { - const useMultilingualModelState = useMultilingualCheckbox.checked; - if (useMultilingualModelState) { - languageDropdown.disabled = false; - taskDropdown.disabled = false; - } else { - languageDropdown.disabled = true; - taskDropdown.disabled = true; - } - browser.storage.local.set({ useMultilingualModelState }); - }); - languageDropdown.addEventListener('change', function() { if (languageDropdown.value === "") { selectedLanguage = null; diff --git a/Audio-Transcription-Firefox/style.css b/Audio-Transcription-Firefox/style.css index 6e743dc..dc6f27b 100644 --- a/Audio-Transcription-Firefox/style.css +++ b/Audio-Transcription-Firefox/style.css @@ -108,4 +108,4 @@ label { .dropdown-container { padding: 10px; -} \ No newline at end of file +} From 17d62272cf9bb00292a557bca85e57c420494b45 Mon Sep 17 00:00:00 2001 From: Sasa Trivic Date: Sun, 4 Feb 2024 17:52:21 +0100 Subject: [PATCH 2/3] Update README.md Remove multilingual from README --- README.md | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index e00dfea..c4712df 100644 --- a/README.md +++ b/README.md @@ -56,7 +56,6 @@ from whisper_live.client import TranscriptionClient client = TranscriptionClient( "localhost", 9090, - is_multilingual=False, lang="en", translate=False, model="small" @@ -64,7 +63,7 @@ client = TranscriptionClient( client("tests/jfk.wav") ``` -This command transcribes the specified audio file (audio.wav) using the Whisper model. It connects to the server running on localhost at port 9090. It can also enable the multilingual feature, allowing transcription in multiple languages. The language option specifies the target language for transcription, in this case, English ("en"). The translate option should be set to `True` if we want to translate from the source language to English and `False` if we want to transcribe in the source language. +This command transcribes the specified audio file (audio.wav) using the Whisper model. It connects to the server running on localhost at port 9090. Using a multilingual model, language for the transcription will be automatically detected. You can also use the language option to specify the target language for the transcription, in this case, English ("en"). The translate option should be set to `True` if we want to translate from the source language to English and `False` if we want to transcribe in the source language. - To transcribe from microphone: ```python @@ -72,22 +71,21 @@ from whisper_live.client import TranscriptionClient client = TranscriptionClient( "localhost", 9090, - is_multilingual=True, lang="hi", translate=True, model="small" ) client() ``` -This command captures audio from the microphone and sends it to the server for transcription. It uses the multilingual option with `hi` as the selected language, enabling the multilingual feature and specifying the target language and task. We use whisper `small` by default but can be changed to any other option based on the requirements and the hardware running the server. +This command captures audio from the microphone and sends it to the server for transcription. It uses the multilingual model with `hi` as the selected language. We use whisper `small` by default but can be changed to any other option based on the requirements and the hardware running the server. - To transcribe from a HLS stream: ```python from whisper_live.client import TranscriptionClient -client = TranscriptionClient(host, port, is_multilingual=True, lang="en", translate=False) +client = TranscriptionClient(host, port, lang="en", translate=False) client(hls_url="http://as-hls-ww-live.akamaized.net/pool_904/live/ww/bbc_1xtra/bbc_1xtra.isml/bbc_1xtra-audio%3d96000.norewind.m3u8") ``` -This command streams audio into the server from a HLS stream. It uses the same options as the previous command, enabling the multilingual feature and specifying the target language and task. +This command streams audio into the server from a HLS stream. It uses the same options as the previous command, using the multilingual model and specifying the target language and task. ## Transcribe audio from browser - Run the server with your desired backend as shown [here](https://github.com/collabora/WhisperLive?tab=readme-ov-file#running-the-server) From f383121ec30b587857350e999d629be6ec46bd30 Mon Sep 17 00:00:00 2001 From: Sasa Trivic Date: Sun, 4 Feb 2024 18:03:41 +0100 Subject: [PATCH 3/3] Remove multilingual option description from the extension readme --- Audio-Transcription-Chrome/README.md | 1 - Audio-Transcription-Firefox/README.md | 1 - 2 files changed, 2 deletions(-) diff --git a/Audio-Transcription-Chrome/README.md b/Audio-Transcription-Chrome/README.md index 7392f73..ec00040 100644 --- a/Audio-Transcription-Chrome/README.md +++ b/Audio-Transcription-Chrome/README.md @@ -26,7 +26,6 @@ To capture the audio in the current tab, we used the chrome `tabCapture` API to ### Options When using the Audio Transcription extension, you have the following options: - **Use Collabora Server**: We provide a demo server which runs the whisper small model. - - **Use Multilingual Model**: Enable this option to utilize the multilingual capabilities of OpenAI-whisper. - **Language**: Select the target language for transcription or translation. You can choose from a variety of languages supported by OpenAI-whisper. - **Task:** Choose the specific task to perform on the audio. You can select either "transcribe" for transcription or "translate" to translate the audio to English. - **Model Size**: Select the whisper model size to run the server with. diff --git a/Audio-Transcription-Firefox/README.md b/Audio-Transcription-Firefox/README.md index be48b78..5e4669e 100644 --- a/Audio-Transcription-Firefox/README.md +++ b/Audio-Transcription-Firefox/README.md @@ -24,7 +24,6 @@ To capture the audio in the current tab, we used the chrome `tabCapture` API to ### Options When using the Audio Transcription extension, you have the following options: - **Use Collabora Server**: We provide a demo server which runs the whisper small model. - - **Use Multilingual Model**: Enable this option to utilize the multilingual capabilities of OpenAI-whisper. - **Language**: Select the target language for transcription or translation. You can choose from a variety of languages supported by OpenAI-whisper. - **Task:** Choose the specific task to perform on the audio. You can select either "transcribe" for transcription or "translate" to translate the audio to English. - **Model Size**: Select the whisper model size to run the server with.