whisperlivekit/audio_processor.py: apply translation to the whole recognized chunk insted of on a token basis

whisperlivekit/audio_processor.py: use space as separator

whisperlivekit/audio_processor.py: translate only the new text coming from transcription

whisperlivekit/core.py: test ctranslate2.Translator with device = cuda

whisperlivekit/core.py: ensure ctranslate2.Translator is loaded in the cpu

whisperlivekit/audio_processor.py: activate translation

whisperlivekit/whisper_streaming_custom/backends.py: use BatchedInferencePipeline in FasterWhisperASR class, and batch_size=16 in transcribe() function, also created WhisperXASR class

whisperlivekit/audio_processor.py: translation controlled by and if/else, added await to call translate_text as async

connected translation with frontend

whisperlivekit/core.py: print args, load model_cascaded_translation from input parameter

whisperlivekit/audio_processor.py: bug fix to translate from transcribed text and show in log messages

whisperlivekit/core.py: load models for translation in class WhisperLiveKit

whisperlivekit/audio_processor.py: define and call translate_text, define translation_tokenizer and translator attributes in class AudioProcessor

reproduced renderLinesWithBuffer on upperCase version

adapted websocket variable

Dockerfile whisperlivekit/core.py: leaving the config to work as ASR in CA

whisperlivekit/core.py: set default task to translate

whisperlivekit/web/live_transcription.html: change default websocket url so it works on HF

Merge branch 'main' of https://github.com/QuentinFuxa/whisper_streaming_web

enhance chunking to handle audio buffer time limits

Logs for https://github.com/QuentinFuxa/WhisperLiveKit/issues/110 https://github.com/QuentinFuxa/WhisperLiveKit/issues/106

update import after moving target file

return silero_vad_iterator.py to whisper_streaming(_custom) package.

Merge pull request #113 from needabetterusername/implement-107

Allow CTranslate2 backend to choose device and compute types.

Merge pull request #109 from QuentinFuxa/needabetterusername/implement-69

Improve WebSocket fallback logic

Implement #107

start implementing frontend part of https://github.com/QuentinFuxa/WhisperLiveKit/pull/80

Corrects 'TranscriptionSegment' object is not subscriptable

solve #100

Solve #95 and #96

0.1.2

update CLI launch

script to lib