 makaveli10
|
20a8a8ad3d
|
update log level to warning
|
2024-02-07 23:26:13 +05:30 |
|
|
makaveli10
|
07387abbc0
|
silence WhisperTRTLLM import warning
|
2024-02-07 23:25:50 +05:30 |
|
|
makaveli10
|
4ecc59783e
|
bump version v0.1.0
|
2024-02-05 22:37:11 +05:30 |
|
|
makaveli10
|
56d19f5469
|
fix: typo; remove multilingual debug stat
|
2024-02-04 14:34:16 +05:30 |
|
|
Sasa Trivic
|
e697574870
|
Remove multilingual from client. Remove multilingual from faster whisper backend. Disable task dropdown when capturing in chrome extension.
|
2024-02-02 13:56:26 +01:00 |
|
|
Sasa Trivic
|
b098b52a4d
|
Merge branch 'main' of github.com:lightwastak3n/WhisperLive
|
2024-02-01 17:37:18 +01:00 |
|
|
Sasa Trivic
|
ad5543b03e
|
Merge remote-tracking branch 'upstream/main'
|
2024-02-01 17:31:35 +01:00 |
|
|
Sasa Trivic
|
32ed089a76
|
Change faster whisper to work with new extension
|
2024-02-01 14:54:29 +01:00 |
|
|
Sasa Trivic
|
e1f531eccf
|
Remove duplicate assignment
|
2024-02-01 13:56:09 +01:00 |
|
|
makaveli10
|
08575a03c2
|
write srt file only for faster_whisper backend
|
2024-02-01 14:22:45 +05:30 |
|
|
makaveli10
|
f590446865
|
Merge remote-tracking branch 'upstream/main' into save_transcript
|
2024-02-01 12:14:09 +05:30 |
|
|
Sasa Trivic
|
36d137888e
|
Merge branch 'collabora:main' into main
|
2024-01-31 18:03:29 +01:00 |
|
|
Sasa Trivic
|
7cc945aded
|
self.client_uid accessed without being defined
|
2024-01-31 16:45:31 +01:00 |
|
|
makaveli10
|
f4027de343
|
add: save_transcript to srt file
|
2024-01-31 17:37:30 +05:30 |
|
|
makaveli10
|
d1754d2c46
|
fix: model_size, no_speech, segment timings
|
2024-01-31 17:37:03 +05:30 |
|
|
makaveli
|
703263b375
|
wamrup tensorrt engine
|
2024-01-29 12:17:27 +05:30 |
|
|
makaveli
|
30d2cffb93
|
load audio for warmup
|
2024-01-29 12:15:39 +05:30 |
|
|
makaveli10
|
3bf5b47947
|
fix: server; remove debug stats
|
2024-01-22 11:47:01 +00:00 |
|
|
makaveli10
|
986823dbef
|
Merge remote-tracking branch 'upstream/main' into tensorrt_backend
|
2024-01-19 10:45:01 -05:00 |
|
|
makaveli10
|
f25ff1785a
|
increase chunk size from 64ms to 256ms
|
2024-01-19 12:02:05 +00:00 |
|
|
makaveli10
|
735d6c7763
|
merge with main
|
2024-01-19 11:43:21 +00:00 |
|
|
makaveli10
|
881fd55776
|
run server with custom model from args
|
2024-01-18 15:02:51 +08:00 |
|
|
makaveli10
|
71d0fe69c6
|
add option to use custom model
|
2024-01-15 23:28:02 +08:00 |
|
|
makaveli10
|
076aebf3b6
|
bump version v0.0.11
|
2024-01-12 15:21:27 +05:30 |
|
|
makaveli10
|
4cf9d95f73
|
merge main
|
2024-01-12 08:17:46 +00:00 |
|
|
makaveli
|
d91330d790
|
Merge branch 'collabora:main' into fix_error_messages
|
2024-01-11 18:18:58 +05:30 |
|
|
makaveli10
|
058c93e55e
|
fix: key error
|
2024-01-11 18:55:43 +08:00 |
|
|
makaveli10
|
647c576e6a
|
update with multilingual option
|
2024-01-11 08:17:56 +00:00 |
|
|
makaveli10
|
244ca9e6ba
|
remove duplicate code
|
2024-01-10 14:14:48 +00:00 |
|
|
makaveli10
|
fd86340f30
|
add: tensorrt backend
|
2024-01-09 18:09:50 +00:00 |
|
|
makaveli10
|
2300eedc8b
|
fix: error messages
|
2024-01-09 13:35:38 +08:00 |
|
|
Chen Hua
|
72ead71eeb
|
feat: set initial_prompt and vad_parameters in the first message
|
2024-01-08 15:33:55 +08:00 |
|
|
Chen Hua
|
32c6a565d7
|
refactor(server): add format_segment helper to standardize timestamp output
|
2024-01-03 12:25:25 +08:00 |
|
|
makaveli
|
e30286c046
|
Merge pull request #83 from Chronoz/fix_exception_on_overflow
fix exception on overflow
|
2024-01-02 19:01:36 +05:30 |
|
|
makaveli10
|
7c0b32b85e
|
bump version 0.0.10
|
2024-01-01 18:12:51 +05:30 |
|
|
华晨
|
02793a93f8
|
feat: Update transcriber to support large-v3 model with 128 mel filters
|
2024-01-01 20:22:37 +08:00 |
|
|
Chronoz
|
e92ddd291a
|
fix exception on overflow
|
2023-12-31 20:59:33 +07:00 |
|
|
华晨
|
71d207a607
|
feat: add large-v3 model
|
2023-12-30 23:19:30 +08:00 |
|
|
makaveli10
|
e006722da7
|
add model size option to client
|
2023-12-20 18:06:02 +05:30 |
|
|
makaveli10
|
402fceb9f3
|
remove emptyline
|
2023-12-15 02:21:09 +08:00 |
|
|
makaveli10
|
09b18e8ab8
|
add model size option from server
|
2023-12-14 22:08:12 +08:00 |
|
|
Jesús Hormigo
|
b6dee4e46e
|
Using ffmpeg-python package instead of requiring having ffmpeg installed in system
|
2023-12-10 19:34:27 +01:00 |
|
|
Jesús Hormigo
|
f3cd20fbf3
|
Support for HLS transcription (resolves #62)
|
2023-12-09 21:24:55 +01:00 |
|
|
makaveli10
|
da86c18205
|
bump version: 0.0.9
|
2023-12-06 15:09:50 +05:30 |
|
|
makaveli10
|
ee80bd21bd
|
update faster_whisper backend
|
2023-11-20 19:04:31 +08:00 |
|
|
makaveli10
|
84122de339
|
add version
|
2023-10-13 16:13:49 +08:00 |
|
|
makaveli10
|
ad37d8c63c
|
add arg to run vad on cpu
|
2023-09-28 23:41:31 +05:30 |
|
|
makaveli10
|
6a087fa1f6
|
Merge remote-tracking branch 'upstream/main' into vad_warnings
|
2023-09-27 20:35:38 +08:00 |
|
|
makaveli10
|
5fb6be41bb
|
allow only CPU Execution
|
2023-09-27 16:17:20 +08:00 |
|
|
makaveli10
|
26b5857747
|
add vad model link to original script
|
2023-09-27 15:44:48 +08:00 |
|