 Jakub Kukul
|
14a7cab8eb
|
Pass patience and beam_size to faster-whisper.
|
2023-10-14 13:51:29 +02:00 |
|
 Marco Vela
|
a5356509b6
|
fix(diarize): key error on empty track
|
2023-10-10 14:50:41 -05:00 |
|
 Mahmoud Ashraf
|
8049dba2f7
|
fix minimum input length for torch wav2vec2 models
|
2023-10-06 00:41:23 +03:00 |
|
 Andrew Bettke
|
79801167ac
|
Fix: Allow vad options to be configurable by correctly passing down to FasterWhisperPipeline.
|
2023-10-05 10:06:34 -04:00 |
|
 Manohar Reddy
|
a0b6459c8b
|
fix: ZeroDivisionError when --print_progress True
|
2023-09-27 20:10:43 +05:30 |
|
 Max Bain
|
2a11ce3ef0
|
Merge pull request #487 from piuy11/main
Update alignment.py
|
2023-09-26 14:17:46 -07:00 |
|
 Remc
|
b17908473d
|
correct 3.0 pyannote weights
|
2023-09-26 17:18:20 +02:00 |
|
 piuy11
|
f137f31de6
|
Update alignment.py
|
2023-09-25 15:33:06 +09:00 |
|
|
Max Bain
|
ffd6167b26
|
Merge pull request #473 from sorgfresser/fix-faster-whisper-threads
|
2023-09-19 16:53:34 -07:00 |
|
 Simon Sorg
|
0ae0d49d1d
|
add faster whisper threading
|
2023-09-14 11:47:51 +02:00 |
|
 darwintree
|
c6d9e6cb67
|
chore(writer): improve text display(ja etc) in json file
|
2023-09-10 22:02:47 +08:00 |
|
 awerks
|
2ca99ce909
|
A solution to long subitles
Example usage:
subtitles_proccessor = SubtitlesProcessor(output["segments"], detected_language, max_line_length = 50, min_char_length_splitter = 35)
subtitles_proccessor.save("subtitles.srt", advanced_splitting = True)
|
2023-09-04 21:49:34 +02:00 |
|
|
Remc
|
15451d0f1c
|
fix: correct defaut_asr_options with new options (patch 0.8)
|
2023-09-04 17:08:19 +02:00 |
|
 陳鈞
|
5223de2a41
|
fix: UnboundLocalError: local variable 'align_language' referenced before assignment
|
2023-08-30 01:11:09 +08:00 |
|
|
陳鈞
|
f505702dc7
|
chore(writer): Join words without spaces for ja, zh
fix #248, fix #310
|
2023-08-30 01:11:09 +08:00 |
|
|
Max Bain
|
9647f60fca
|
Merge branch 'main' into add-merge-chunk-size-as-argument
|
2023-08-29 10:05:05 -06:00 |
|
|
Max Bain
|
a8bfac6bef
|
Merge pull request #427 from awerks/main
Update alignment.py
|
2023-08-29 10:03:46 -06:00 |
|
|
陳鈞
|
eb771cf56d
|
feat: Add merge chunks chunk_size as arguments.
Suggest from https://github.com/m-bain/whisperX/issues/200#issuecomment-1666507780
|
2023-08-29 23:09:02 +08:00 |
|
 invisprints
|
cc81ab7db7
|
fix missing prefix
Fixed missing the speaker part when enable --highlight_words
|
2023-08-25 12:08:16 +08:00 |
|
|
awerks
|
4e28492dbd
|
Update alignment.py
|
2023-08-17 14:57:53 +02:00 |
|
|
awerks
|
6cb7267dc2
|
Update alignment.py
|
2023-08-17 14:56:54 +02:00 |
|
|
awerks
|
abbb66b58e
|
Update alignment.py
|
2023-08-17 14:53:53 +02:00 |
|
|
awerks
|
ea7bb91a56
|
Update asr.py
|
2023-08-17 14:49:57 +02:00 |
|
|
awerks
|
d2d840f06c
|
Update utils.py
|
2023-08-17 14:45:23 +02:00 |
|
|
Max Bain
|
0a1137e41c
|
Merge pull request #429 from sorgfresser/no-segments-writer
fix writer fail on segments 0
|
2023-08-17 13:20:38 +01:00 |
|
|
Simon Sorg
|
0767597bff
|
fix writer fail on segments 0
|
2023-08-17 14:18:16 +02:00 |
|
|
awerks
|
cb3ed4ab9d
|
Update transcribe.py
|
2023-08-16 16:22:29 +02:00 |
|
|
awerks
|
65688208c9
|
Update alignment.py
|
2023-08-16 16:18:00 +02:00 |
|
|
awerks
|
72685d0398
|
Update asr.py
|
2023-08-16 16:15:24 +02:00 |
|
|
awerks
|
1bb4839b0f
|
Update alignment.py
|
2023-08-16 16:13:28 +02:00 |
|
|
awerks
|
4acb5b3abc
|
Update asr.py
|
2023-08-16 16:11:46 +02:00 |
|
|
awerks
|
14e593f60b
|
Update alignment.py
|
2023-08-16 16:08:25 +02:00 |
|
|
Max Bain
|
18d5fdc995
|
Add telugu language to alignment.py
|
2023-08-10 12:13:52 +01:00 |
|
 Ayushi-Desynova
|
423667f00b
|
Update alignment.py
|
2023-08-09 17:08:56 +05:30 |
|
|
Max Bain
|
1b092de19a
|
Merge pull request #395 from Joemgu7/main
Fix repeat transcription on different languages and proper suppress_numerals use
|
2023-08-02 13:44:27 +01:00 |
|
 Dudu Asulin
|
9e3145cead
|
more
|
2023-08-02 10:36:56 +03:00 |
|
|
Dudu Asulin
|
577db33430
|
more
|
2023-08-02 10:35:20 +03:00 |
|
|
Dudu Asulin
|
da6ed83dc9
|
more
|
2023-08-02 10:34:42 +03:00 |
|
|
Dudu Asulin
|
8de0e2af51
|
make diarization faster
|
2023-08-02 10:11:43 +03:00 |
|
 briguetjo
|
225f6b4d69
|
fix suppress_numerals
|
2023-07-29 19:34:51 +02:00 |
|
|
briguetjo
|
864976af23
|
fix issue by resetting tokenizer
|
2023-07-29 18:56:33 +02:00 |
|
|
briguetjo
|
9d736dca1c
|
add some warning if languages do not match
|
2023-07-29 18:20:59 +02:00 |
|
|
briguetjo
|
d87f6268d0
|
fix preset language
|
2023-07-29 18:13:36 +02:00 |
|
|
Max Bain
|
54504a2be8
|
Merge pull request #374 from abCods/main
Add Urdu model support for alignment
|
2023-07-24 10:47:52 +01:00 |
|
|
Max Bain
|
8c0fee90d3
|
Update alignment.py
|
2023-07-24 10:47:41 +01:00 |
|
 Mark Berger
|
48e7caad77
|
Update transcribe.py -> small change in batch_size description
Changed the description of the `batch_size` parameter.
|
2023-07-24 11:45:38 +02:00 |
|
 Ahmad Bilal
|
e6ecbaa68f
|
Remove spacing
|
2023-07-20 03:20:47 +05:00 |
|
|
Ahmad Bilal
|
e92325b7eb
|
Remove the fix
|
2023-07-20 03:19:37 +05:00 |
|
|
Ahmad Bilal
|
eb712f3999
|
Rectify refernce to the word
|
2023-07-20 02:54:06 +05:00 |
|
|
Ahmad Bilal
|
30eff5a01f
|
Replace double quotes to single for JSON parsing
|
2023-07-20 02:32:37 +05:00 |
|