cjones/WhisperLive
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
451 Commits 2 Branches 20 Tags
2eff360b9e339a2897bd0b9fc5ce27325dcd6f36
Commit Graph

139 Commits

Author SHA1 Message Date
makaveli10 2eff360b9e Support loading hf models 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-11-26 11:14:18 +05:30
makaveli10 a1650eaa4f Fix client tests to write srt file 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-11-19 13:31:55 +05:30
makaveli10 a6523b6b71 Minor fixes for better punctuations 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-11-19 02:13:11 -05:00
makaveli10 778a9c5903 Upgrade faster-whisper 1.1.0rc0 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-11-14 10:07:37 -05:00
makaveli10 81c57ae40c Send completed bool with each segment 
Completed bool represents if the segment is completely processed by the server

Signed-off-by: makaveli10 <suryanvineet47@gmail.com>
 2024-11-05 18:11:32 +05:30
makaveli10 0d74790c67 Expose ClientManager arguments to be passed from client 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-10-10 08:37:45 -04:00
makaveli bc070d6688 Bump version 0.5.1 2024-09-05 09:34:30 +05:30
makaveli10 380f07394b Set compute_type based on device capability 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-09-03 00:47:38 -04:00
makaveli10 01c6bc1ecd Initialize last_segment to None 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-08-30 07:47:03 -04:00
makaveli10 4870e9fb9e Make text logging optional 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-08-08 06:09:44 -04:00
makaveli10 fac62aaccc Fix hallucinations with no_speech_thres 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-08-08 06:05:12 -04:00
Sean Dang abfe830eee Fix deadlock issue in FFmpeg subprocess by ensuring stderr is consumed 2024-07-11 23:30:44 +07:00
makaveli cb392cbb93 Merge pull request #247 from makaveli10/pin_sliero_vad_model_version 
Pin silero VAD onnx model version to v4.0
 2024-07-09 12:58:27 +05:30
makaveli10 26c517021f Pin silero VAD onnx model version to v4.0 
Signed-off-by: makaveli10 <suryanvineet47@gmail.com>
 2024-07-02 11:01:40 +05:30
berkaybilik 2f1c934ea2 always use the BackendType enum to reference the backend inside the TranscriptionServer 2024-06-27 00:20:17 +01:00
berkaybilik b220ccb330 fixed reference before assignment error/warning 2024-06-27 00:11:06 +01:00
berkaybilik 5e3906fc7b use enum to validate backend validity in server.run 2024-06-26 23:59:07 +01:00
makaveli 815441e8bb Bump version v0.5.0 2024-06-07 11:21:28 +05:30
makaveli 5b9bc2bc0e Merge pull request #223 from peldszus/single-model-mode 
Single model mode
 2024-06-07 11:10:52 +05:30
makaveli 5e2421118d Merge pull request #227 from makaveli10/update_tensorrt_llm 
Update tensorrt llm to v0.9.0
 2024-06-05 08:50:26 +05:30
makaveli10 f73a146eb9 Update TensorRT backend tensorrt_llm==0.9.0 
Signed-off-by: makaveli10 <vineet.suryan@collabora.com>
 2024-06-03 05:24:41 -04:00
chien-liu cfba5b3e54 Expose the srt file location of Transcription client 2024-06-01 00:14:59 +02:00
Andreas Peldszus 3a96f60006 Raise error for invalid model paths 2024-05-31 15:06:54 +02:00
Andreas Peldszus 3c09289dea Add single model mode for custom models 
- Use a threadlock around the model in single model mode
 2024-05-31 15:06:47 +02:00
makaveli10 3d043dc906 Remove flake8 warning suppression 
Signed-off-by: makaveli10 <suryanvineet47@gmail.com>
 2024-05-28 21:29:38 +05:30
makaveli10 9d2ea75247 Refactor to make record function more readable 
Signed-off-by: makaveli10 <suryanvineet47@gmail.com>
 2024-05-28 11:06:49 +05:30
makaveli10 225a98be0c Ignore linting as this file is a copy from faster_whisper 
Signed-off-by: makaveli10 <suryanvineet47@gmail.com>
 2024-05-28 11:06:49 +05:30
makaveli10 61d07edabb Make writing output audio file optional when using microphone 
Signed-off-by: makaveli10 <suryanvineet47@gmail.com>
 2024-05-28 11:06:49 +05:30
dshepelev15 615c9c7aed Add support for RTSP stream 2024-05-17 17:32:09 +03:00
fraic f78fc473c5 Add option: save network stream to local file while transcribing 2024-03-25 19:11:24 +08:00
makaveli 0dfbdb2477 bump version v0.4.1 2024-03-22 12:30:42 +05:30
makaveli10 66b5dc7c15 Merge remote-tracking branch 'upstream/main' into fix_client_close 2024-03-22 12:13:44 +05:30
makaveli10 0f1d36fc06 fix: microphone client close 2024-03-22 12:13:27 +05:30
John Sichi fe1640695c Don't clear server_error flag on close. 2024-03-21 13:28:18 +09:00
makaveli 8d77f0fa5a bump version v0.4.0 2024-03-20 12:04:38 +05:30
John Sichi 37d7f2ed66 Merge branch 'main' into tee-client 2024-03-13 20:12:51 +09:00
John Sichi 5b32dc4130 Fix default value for multicast. 2024-03-10 21:02:50 +09:00
John Sichi 3b15dc76b4 Add support for processing same audio stream via multiple clients with different tasks. 2024-03-10 20:44:15 +09:00
FlippFuzz 4d477e35e7 Handle failure on systems without microphones 
Catch the OSError and print a WARN log.
 2024-03-10 19:43:53 +08:00
makaveli10 02d4566289 upgrade faster whisper 1.0.1 2024-03-04 07:35:43 +00:00
makaveli 9e5ab408cd bump version 0.3.0 2024-02-28 23:39:44 +05:30
makaveli10 18b6168807 fix: cpu usage issue 2024-02-28 13:55:37 +05:30
makaveli10 a41e714801 fix: lanuguage, task prefix in decoder start ids 2024-02-26 23:31:19 -05:00
makaveli c067224474 bump version 0.2.1 2024-02-22 11:16:10 +05:30
makaveli 308ac1cff7 bump version 0.2.0 2024-02-22 11:03:30 +05:30
makaveli10 dc22b7da9f add srt_file_path option 2024-02-20 11:53:45 +05:30
makaveli10 b42ced9816 fix: tests for end of speech message while mocking pyaudio 2024-02-16 20:31:38 +05:30
makaveli10 78da3f6750 Merge branch 'code_formatting' into vad_option 2024-02-16 17:29:37 +05:30
makaveli10 147e97002e clear_screen for updated transcript 2024-02-15 18:56:14 +05:30
makaveli10 01dc69e068 close when end of audio from client 2024-02-15 18:07:19 +05:30