choomegan
|
64e44fb24f
|
fix: logic of adding of pcm_array to diarization_queue
|
2025-07-15 15:33:41 +08:00 |
|
Quentin Fuxa
|
9ff513093b
|
simulstreaming uses empty space as separator
|
2025-07-04 17:03:01 +02:00 |
|
Quentin Fuxa
|
aad2c55d8c
|
download_simulstreaming_backend.py now downloads files in the correct lib dir
|
2025-07-03 11:07:28 +02:00 |
|
Quentin Fuxa
|
2f177c4a3b
|
add __init__.py file to simul_whisper assets directory
|
2025-07-03 10:41:12 +02:00 |
|
Quentin Fuxa
|
b362eccb23
|
new command to get simulstreaming backend
|
2025-07-03 10:24:02 +02:00 |
|
Quentin Fuxa
|
5daaf77258
|
add download script for SimulStreaming backend
|
2025-07-03 10:14:45 +02:00 |
|
Quentin Fuxa
|
36cc4412c3
|
update LICENSE with SimulStreaming dual licensing terms; include in .gitignore additional stuff
|
2025-07-03 09:21:38 +02:00 |
|
Quentin Fuxa
|
e1d4bf7e94
|
modify import paths in simul whisper backend so that it works in lib mode
|
2025-07-01 20:34:47 +02:00 |
|
Quentin Fuxa
|
62bf28949e
|
compatible with the latest version of simulstreaming
|
2025-07-01 20:10:45 +02:00 |
|
Quentin Fuxa
|
1e3fab9550
|
copy non python files from simulstreaming when installing package
|
2025-07-01 19:14:23 +02:00 |
|
Quentin Fuxa
|
f25de6d8a4
|
ffmpeg-python is not used anymore - ffmpeg is directly called through create_subprocess_exec
|
2025-07-01 18:53:35 +02:00 |
|
Quentin Fuxa
|
8a175e79d8
|
Merge branch 'main' of https://github.com/QuentinFuxa/whisper_streaming_web
|
2025-07-01 18:52:26 +02:00 |
|
Quentin Fuxa
|
dc37b44486
|
add _read_stderr to empty the stderr
|
2025-07-01 17:05:58 +02:00 |
|
Quentin Fuxa
|
2d1df92aa7
|
Merge pull request #145 from SlavikCA/port-fix
fix port for WS link; use correct HF build arg
|
2025-07-01 14:16:58 +02:00 |
|
Quentin Fuxa
|
2c1a603e38
|
ffmpeg is managed in a thread in FFmpegManager to prevent the all from crashing when an error occurs
|
2025-07-01 11:19:10 +02:00 |
|
Quentin Fuxa
|
774cee036b
|
increase timeout from 2 to 20s for ffmpeg stdin flush and writing
|
2025-06-30 18:28:50 +02:00 |
|
Quentin Fuxa
|
d22916988e
|
add SIMULSTREAMING_ERROR_AND_INSTALLATION_INSTRUCTIONS for instructions when simulstreaming files are not there
|
2025-06-30 17:42:45 +02:00 |
|
slavik.fursov
|
5b8ad94dde
|
fix port for WS link; use correct HF build arg
|
2025-06-30 08:15:51 -07:00 |
|
Quentin Fuxa
|
f668570292
|
Trim buffer when no new ASR tokens are issued
|
2025-06-30 11:55:07 +02:00 |
|
Quentin Fuxa
|
7c0768e8f3
|
bump version to 0.2.1; enhance error message for simulstreaming missing dependencies
|
2025-06-27 14:06:35 +02:00 |
|
Quentin Fuxa
|
b42d8b2692
|
add dual license warning indication when using simulstreaming backend
|
2025-06-27 10:00:19 +02:00 |
|
Quentin Fuxa
|
8e30e8010a
|
correct timing (lag) calculations in SimulStreamingASR and SimulStreamingOnlineProcessor
|
2025-06-26 00:13:44 +02:00 |
|
Quentin Fuxa
|
bfec335a5f
|
restore a functionnal buffer_diarization
|
2025-06-25 23:38:23 +02:00 |
|
Quentin Fuxa
|
6867041254
|
1rst version of SimulStreaming backend. many improvements needed
|
2025-06-25 17:59:46 +02:00 |
|
Quentin Fuxa
|
8532a91c7a
|
add segmentation and embedding model options to configuration
|
2025-06-19 16:29:25 +02:00 |
|
Quentin Fuxa
|
b01b81bad0
|
improve diarization with lag diarization substraction
|
2025-06-19 16:18:49 +02:00 |
|
Quentin Fuxa
|
0f79d442ee
|
improve diarization speed + Use punctuation to better align speakers and diarization
|
2025-06-19 13:03:29 +02:00 |
|
Quentin Fuxa
|
993a83546a
|
core refactoring
|
2025-06-16 16:13:57 +02:00 |
|
Quentin Fuxa
|
f7644268c1
|
Message when launching transcription and no audio is detected
|
2025-05-28 13:25:49 +02:00 |
|
Quentin Fuxa
|
34e8fe260e
|
lag information in real time even when no audio is detected
|
2025-05-28 12:25:47 +02:00 |
|
Quentin Fuxa
|
6797b88176
|
Error handling for missing FFmpeg in start_ffmpeg_decoder
|
2025-05-28 11:43:30 +02:00 |
|
Quentin Fuxa
|
46770efd6c
|
correct error when using VAC
|
2025-05-28 11:43:18 +02:00 |
|
Quentin Fuxa
|
fea3c3553c
|
logging in ASR proc. includes internal buffer duration and transcription lag
|
2025-05-07 11:45:00 +02:00 |
|
Quentin Fuxa
|
d6d65a663b
|
errors handling when end of transcription
|
2025-05-07 10:56:04 +02:00 |
|
Quentin Fuxa
|
083d5b2f44
|
uses sentinel object when end of transcription, to properly terminate tasks
|
2025-05-07 10:55:44 +02:00 |
|
Quentin Fuxa
|
8e4674b093
|
End of transcription : Properly sends signal back to the endpoint
|
2025-05-07 10:55:12 +02:00 |
|
Quentin Fuxa
|
b56fcffde1
|
Solves stdin flushes blocking IOhttps://github.com/QuentinFuxa/WhisperLiveKit/issues/110
https://github.com/QuentinFuxa/WhisperLiveKit/issues/106
https://github.com/QuentinFuxa/WhisperLiveKit/issues/90
https://github.com/QuentinFuxa/WhisperLiveKit/issues/87
https://github.com/QuentinFuxa/WhisperLiveKit/issues/81
https://github.com/QuentinFuxa/WhisperLiveKit/issues/2
|
2025-04-12 15:25:46 +02:00 |
|
Quentin Fuxa
|
2def194893
|
add ssl certificate and key file arguments to parser
|
2025-04-11 12:20:22 +02:00 |
|
Quentin Fuxa
|
29978da301
|
adds ssl possibility in basic server
|
2025-04-11 12:20:08 +02:00 |
|
Quentin Fuxa
|
b708890788
|
protocol default to ws
|
2025-04-11 12:14:14 +02:00 |
|
Quentin Fuxa
|
3ac4c514cf
|
remove temp_kit method to get args. uvicorn reload to False for better perfs
|
2025-04-11 12:02:52 +02:00 |
|
Chris Margach
|
d53b7a323a
|
update sample html to use wss in case of https
|
2025-04-10 13:46:52 +09:00 |
|
Chris Margach
|
02de5993e6
|
allow passing of cert and key locations to uvicorn via package
|
2025-04-10 13:42:30 +09:00 |
|
Quentin Fuxa
|
d94560ef37
|
Merge branch 'main' of https://github.com/QuentinFuxa/whisper_streaming_web
|
2025-04-09 11:38:57 +02:00 |
|
Quentin Fuxa
|
0b43035701
|
enhance chunking to handle audio buffer time limits
|
2025-04-09 11:34:59 +02:00 |
|
Quentin Fuxa
|
704170ccf3
|
Logs for https://github.com/QuentinFuxa/WhisperLiveKit/issues/110 https://github.com/QuentinFuxa/WhisperLiveKit/issues/106
https://github.com/QuentinFuxa/WhisperLiveKit/issues/90
https://github.com/QuentinFuxa/WhisperLiveKit/issues/87
https://github.com/QuentinFuxa/WhisperLiveKit/issues/81
https://github.com/QuentinFuxa/WhisperLiveKit/issues/2
|
2025-04-09 11:34:27 +02:00 |
|
Chris Margach
|
51e6a6f6f9
|
update import after moving target file
|
2025-04-09 13:33:39 +09:00 |
|
Chris Margach
|
f6e53b2fab
|
return silero_vad_iterator.py to whisper_streaming(_custom) package.
|
2025-04-09 11:59:21 +09:00 |
|
Quentin Fuxa
|
40cca184c1
|
Merge pull request #113 from needabetterusername/implement-107
Allow CTranslate2 backend to choose device and compute types.
|
2025-04-07 14:42:57 +02:00 |
|
Chris Margach
|
9c9c179684
|
Allow CTranslate2 backend to choose device and compute types.
|
2025-04-07 14:47:29 +09:00 |
|