Commit Graph

82 Commits

Author SHA1 Message Date
m-bain 4cdf7ef856 Merge pull request #48 from Barabazs/main
doc: format checklist
2023-02-01 10:26:58 +00:00
Barabazs d83c74a79f doc: format checklist 2023-01-29 16:07:58 +01:00
m-bain acaefa09a1 Merge pull request #46 from Barabazs/main
Add sponsor link to sidebar
2023-01-28 19:05:36 +00:00
Max Bain 76f79f600a fix short seg timestamps bug 2023-01-28 19:04:19 +00:00
Barabazs 33073f9bba Create FUNDING.yml 2023-01-28 19:43:27 +01:00
Max Bain 50f3965fdb fix tsv file ext 2023-01-28 17:39:07 +00:00
Max Bain df2b1b70cb increase vad cut default 2023-01-28 14:49:53 +00:00
Max Bain c19cf407d8 handle non-alignable whole segments 2023-01-28 13:53:03 +00:00
Max Bain 8081ef2dcd add custom vad binarization for vad cut 2023-01-28 00:22:33 +00:00
Max Bain c6dbac76c8 cut up vad segments when too long to prevent OOM 2023-01-28 00:01:39 +00:00
Max Bain 69673eb39b buy-me-a-coffee 2023-01-27 15:12:49 +00:00
Max Bain 5b8c8a7bd3 pandas fix 2023-01-27 15:05:08 +00:00
Max Bain 7f2159a953 Merge branch 'main' of https://github.com/m-bain/whisperX into main 2023-01-26 10:46:36 +00:00
Max Bain 16d24b1c96 only pad timestamps if not using VAD 2023-01-26 10:46:13 +00:00
m-bain d20a2a4ea2 typo in --diarize flag 2023-01-26 10:28:54 +00:00
m-bain 312f1cc50c Merge pull request #40 from MahmoudAshraf97/main
Added arguments and instructions to enable the usage VAD and Diarization
2023-01-26 00:34:03 +00:00
Mahmoud Ashraf 99b6e79fbf Update README.md
added additional instructions to use PyAnnote modules
2023-01-26 00:56:10 +02:00
Mahmoud Ashraf e7773358a3 Update transcribe.py
added the ability to include HF access token in order to use PyAnnote models
2023-01-26 00:42:35 +02:00
Mahmoud Ashraf 6b2aa4ff3e Merge pull request #1 from MahmoudAshraf97/patch-1
Update README.md
2023-01-26 00:37:38 +02:00
Mahmoud Ashraf c3de5e9580 Update README.md
fixed model name
2023-01-26 00:36:29 +02:00
Max Bain 58d7191949 add diarize 2023-01-25 19:40:41 +00:00
Max Bain 286a2f2c14 clean up logic, use pandas where possibl 2023-01-25 18:42:52 +00:00
Max Bain eec6d1f8d8 missing word timestamps 2023-01-24 16:37:19 +00:00
Max Bain d1600e5b0f Merge branch 'main' of https://github.com/m-bain/whisperX into main
Conflicts:
	whisperx/transcribe.py
	whisperx/utils.py
2023-01-24 15:38:05 +00:00
Max Bain d395c21b83 new logic, diarization, vad filtering 2023-01-24 15:02:08 +00:00
Max Bain ba102feb7f vad filter 2023-01-20 12:54:20 +00:00
m-bain 4569cb982a fix file_ass display bug
sentence start time on .ass files had a bug where if the first word did not have a timestamp, it would set sentence start_time to 0, but this needs to be the local 0 not actual file 0 (i.e. it should be segment['start'])
2023-01-12 12:57:12 +00:00
m-bain ce281eb6f6 Merge pull request #28 from aosfatos/update/wav2vec2-large-xlsr-53-portuguese
Update Portuguese model to wav2vec2-large-xlsr-53-portuguese
2023-01-12 09:10:02 +00:00
Rhenan Bartels 7adead16e0 Update pt model to wav2vec2-large-xlsr-53-portuguese 2023-01-11 19:50:34 -03:00
m-bain a4edb130ef Merge pull request #27 from FelippeChemello/main
Add PT (pt-br) align support
2023-01-11 15:35:15 +00:00
Felippe Chemello 7459bf8ad0 Add PT (pt-br) align support 2023-01-11 12:11:41 -03:00
m-bain d51353a4b6 uncomment .ass 2023-01-08 18:02:36 +00:00
Max Bain 78c87d3bfd handle negative / tiny duration segments, final 2023-01-08 14:01:10 +00:00
Max Bain a6eb33778b additional waveform segment check 2023-01-08 12:24:35 +00:00
Max Bain 857bcca238 Merge branch 'main' of https://github.com/m-bain/whisperX into main 2023-01-07 15:00:22 +00:00
Max Bain 44b62064f6 fix starting timestamp for multiple fail-to-aligned words 2023-01-07 14:59:11 +00:00
m-bain 2aa074e0e6 remove duplicate line 2023-01-05 13:12:11 +00:00
Max Bain 5a668a7d80 fallback on whisper alignment failures, update readme 2023-01-05 11:15:19 +00:00
m-bain 93d661f2e4 fix whisper hallucination outside of audio length 2022-12-29 10:54:23 +00:00
m-bain 644b04e8d1 Merge pull request #13 from egorsmkv/patch-1
Add Ukrainian wav2vec2 model
2022-12-25 20:32:56 +00:00
Yehor Smoliakov 97526f1111 Add Ukrainian wav2vec2 model 2022-12-24 15:05:13 +02:00
Max Bain c912f96ed3 add examples.md 2022-12-23 00:50:32 +00:00
Max Bain c6fa7df3cc add chinese, dutch. python usage. readme update 2022-12-23 00:41:12 +00:00
Max Bain e909f2f766 support huggingface + model select based on lang. 2022-12-20 19:54:55 +00:00
Yasutaka Odo 8b2f40d02a Change resolution for Japanese example video 2022-12-21 02:44:11 +09:00
Yasutaka Odo 93e568b3bf replace magic strings 2022-12-21 02:11:08 +09:00
Yasutaka Odo d7546def91 fix errors when recognizing non-japanese audios 2022-12-21 01:42:45 +09:00
Yasutaka Odo 7a3575dfdf fix formatting 2022-12-21 01:23:02 +09:00
Yasutaka Odo c8000f6e3f resolve conflicts 2022-12-21 01:20:35 +09:00
Yasutaka Odo 2ad813c57d undo unnecessary formatting 2022-12-21 01:03:52 +09:00