vlad.os/whisperx-rocm-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • befe2b242e torch 2+ Max Bain 2023-06-07 22:43:29 +01:00
  • f9c5ff9f08 Merge pull request #309 from Ca-ressemble-a-du-fake/patch-1 Max Bain 2023-06-07 11:50:05 +01:00
  • d39c1b2319 add "aud" to output_format Max Bain 2023-06-07 11:48:49 +01:00
  • b13778fefd make aud optional Max Bain 2023-06-07 11:47:49 +01:00
  • 076ff96eb2 Add Audacity export CaraDuf 2023-06-07 05:49:49 +02:00
  • 0c84c26d92 Merge pull request #303 from m-bain/v3 Max Bain 2023-06-05 15:46:26 +01:00
  • d7f1d16f19 suppress numerals change logic Max Bain 2023-06-05 15:44:17 +01:00
  • 74a00eecd7 suppress numerals fix Max Bain 2023-06-05 15:33:04 +01:00
  • b026407fd9 Merge branch 'v3' of https://github.com/m-bain/whisperX into v3 Max Bain 2023-06-05 15:30:02 +01:00
  • a323cff654 --suppress_numerals option, ensures non-numerical words, for wav2vec2 alignment Max Bain 2023-06-05 15:27:42 +01:00
  • 93ed6cfa93 interspeech Max Bain 2023-06-01 16:54:16 +01:00
  • 9797a67391 Merge pull request #294 from SohaibAnwaar/fix/typehint-bug-fix Max Bain 2023-05-30 11:13:22 +01:00
  • 5a4382ae4d fix: Bug in type hinting Master X 2023-05-30 15:11:07 +05:00
  • ec6a110cdf Merge pull request #290 from m-bain/main Max Bain 2023-05-29 12:55:24 +01:00
  • 8d8c027a92 Merge pull request #278 from Mr-Turtleeeee/add_align_for_vi Max Bain 2023-05-29 12:54:37 +01:00
  • 4cbd3030cc no sentence split on mr. mrs. dr... Max Bain 2023-05-29 12:48:14 +01:00
  • 1c528d1a3c Merge pull request #284 from prameshbajra/main Max Bain 2023-05-27 11:19:13 +01:00
  • c65e7ba9b4 Merge pull request #280 from Thebys/patch-1 Max Bain 2023-05-27 11:18:27 +01:00
  • 5a47f458ac Added download path parameter. prameshbajra 2023-05-27 11:38:54 +02:00
  • f1032bb40a VAD unequal stack size, remove debug change Max Bain 2023-05-26 20:39:19 +01:00
  • bc8a03881a Merge pull request #281 from m-bain/v3 Max Bain 2023-05-26 20:37:57 +01:00
  • 42b4909bc0 fix Unequal Stack Size VAD error Max Bain 2023-05-26 20:36:03 +01:00
  • bb15d6b68e Add Czech alignment model Thebys 2023-05-26 21:17:01 +02:00
  • 23d405e1cf Merge branch 'main' into add_align_for_vi Max Bain 2023-05-26 17:14:09 +01:00
  • 17e2f7f859 Merge pull request #277 from Boulaouaney/add-Korean-alignment-model Max Bain 2023-05-26 17:12:47 +01:00
  • 1d9d630fb9 added Korean wav2vec2 model Youssef Boulaoaune 2023-05-26 20:33:16 +09:00
  • 9c042c2d28 Add war2vec model for Vietnamese iambestfeeddddd 2023-05-26 16:46:55 +07:00
  • a23f2aa3f7 Merge pull request #269 from sorgfresser/transcribe_keywords Max Bain 2023-05-21 12:08:44 +01:00
  • 7c5468116f Merge branch 'm-bain:main' into transcribe_keywords Simon 2023-05-20 16:03:40 +02:00
  • a1c705b3a7 fix tokenizer is None Simon 2023-05-20 15:52:45 +02:00
  • 29a5e0b236 Merge pull request #266 from sorgfresser/main Max Bain 2023-05-20 14:45:34 +01:00
  • 715435db42 add tokenizer is None case Simon 2023-05-20 15:42:21 +02:00
  • 1fc965bc1a add task, language keyword to transcribe Simon 2023-05-20 15:30:25 +02:00
  • 74b98ebfaa ensure device_index not None Simon 2023-05-20 13:11:30 +02:00
  • 53396adb21 add device_index Simon 2023-05-20 13:02:46 +02:00
  • 63fb5fc46f Suggest using pytorch-cuda 11.8 instead of 11.7 Tijs Zwinkels 2023-05-16 12:07:09 +02:00
  • d8a2b4ffc9 Merge pull request #246 from m-bain/v3 Max Bain 2023-05-13 12:18:09 +01:00
  • 9ffb7e7a23 Merge branch 'v3' of https://github.com/m-bain/whisperX into v3 Max Bain 2023-05-13 12:16:33 +01:00
  • fd8f1003cf add translate, fix word_timestamp error Max Bain 2023-05-13 12:14:06 +01:00
  • 46b416296f Merge pull request #123 from koldbrandt/danish_alignment Max Bain 2023-05-09 23:10:24 +01:00
  • 7642390d0a Merge branch 'main' into danish_alignment Max Bain 2023-05-09 23:10:13 +01:00
  • 8b05ad4dae Merge pull request #235 from sorgfresser/main Max Bain 2023-05-09 23:05:02 +01:00
  • 5421f1d7ca remove v3 tag on pip install Max Bain 2023-05-09 13:42:50 +01:00
  • 91e959ec4f Merge branch 'm-bain:main' into main Simon 2023-05-08 20:46:25 +02:00
  • eabf35dff0 Custom result types Simon 2023-05-08 20:45:34 +02:00
  • 4919ad21fc Merge pull request #233 from sorgfresser/main Max Bain 2023-05-08 19:05:47 +01:00
  • b50aafb17b Fix tuple unpacking Simon 2023-05-08 20:03:42 +02:00
  • 2efa136114 update python usage example Max Bain 2023-05-08 17:20:38 +01:00
  • 0b839f3f01 Update README.md Max Bain 2023-05-07 20:36:08 +01:00
  • 1caddfb564 Merge pull request #225 from m-bain/v3 Max Bain 2023-05-07 20:31:16 +01:00
  • 7ad554c64f Merge branch 'main' into v3 Max Bain 2023-05-07 20:30:57 +01:00
  • 4603f010a5 update readme, setup, add option to return char_timestamps Max Bain 2023-05-07 20:28:33 +01:00
  • 24008aa1ed fix long segments, break into sentences using nltk, improve align logic, improve diarize (sentence-based) Max Bain 2023-05-07 15:32:58 +01:00
  • 07361ba1d7 add device to dia pipeline @sorgfresser Max Bain 2023-05-05 11:53:51 +01:00
  • 4e2ac4e4e9 torch2.0, remove compile for now, round to times to 3 decimal Max Bain 2023-05-04 20:38:13 +01:00
  • d2116b98ca Merge pull request #210 from sorgfresser/v3 Max Bain 2023-05-04 20:32:06 +01:00
  • d8f0ef4a19 Set diarization device manually Simon 2023-05-04 16:25:34 +02:00
  • 1b62c61c71 Merge pull request #216 from aramlang/blank_id-fix Max Bain 2023-05-04 01:13:23 +01:00
  • 2d59eb9726 Add torch compile to log mel spectrogram Simon 2023-05-03 23:17:44 +02:00
  • cb53661070 Enable Hebrew support aramlang 2023-05-03 11:26:12 -05:00
  • 2a6830492c Fix pyannote to specific commit Simon 2023-05-02 20:25:56 +02:00
  • da3aabe181 Merge branch 'm-bain:v3' into v3 Simon 2023-05-02 18:55:43 +02:00
  • 067189248f Use pyannote develop branch and torch version 2 Simon 2023-05-02 18:44:43 +02:00
  • b666523004 add v3 pre-release comment, and v4 progress update Max Bain 2023-05-02 15:10:40 +01:00
  • 69e038cbc4 Merge pull request #209 from SohaibAnwaar/feat-dockerfile Max Bain 2023-05-02 14:55:30 +01:00
  • 9fb51412c0 Merge pull request #208 from arnavmehta7/patch-1 Max Bain 2023-05-02 10:55:13 +01:00
  • a693a779fa feat: adding the docker file sohaibanwaar 2023-05-02 13:28:20 +05:00
  • 64ca208cc8 Fixed the word_start variable not initialized bug. Arnav Mehta 2023-05-02 13:13:02 +05:30
  • 5becc99e56 Version bump pyannote, pytorch Simon 2023-05-01 13:47:41 +02:00
  • e24ca9e0a2 Merge pull request #205 from prashanthellina/v3-fix-diarization Max Bain 2023-04-30 21:08:45 +01:00
  • 601c91140f references #202, attempt to fix speaker diarization failing in v3 Prashanth Ellina 2023-04-30 17:33:24 +00:00
  • 31a9ec7466 Merge pull request #204 from sorgfresser/v3 Max Bain 2023-04-30 18:29:46 +01:00
  • b9c8c5072b Pad language detection if audio is too short Simon 2023-04-30 18:34:18 +02:00
  • a903e57cf1 Merge pull request #199 from thomasmol/v3 Max Bain 2023-04-29 23:35:42 +01:00
  • cb176a186e added num_workers to fix pickling error Thomas Mol 2023-04-29 19:51:05 +02:00
  • 5b85c5433f Update setup.py Max Bain 2023-04-28 16:47:04 +01:00
  • cc7e168d2b add checkout command m-bain 2023-04-25 12:14:23 +01:00
  • db97f29678 update pip install m-bain 2023-04-25 11:19:23 +01:00
  • 25be8210e5 add v3 tag for install m-bain 2023-04-25 10:07:34 +01:00
  • 0efad26066 pass compute_type Max Bain 2023-04-24 21:26:44 +01:00
  • 2a29f0ec6a add compute types Max Bain 2023-04-24 21:24:22 +01:00
  • 558d980535 v3 init Max Bain 2023-04-24 21:08:43 +01:00
  • da458863d7 allow custom model_dir for torchaudio models Max Bain 2023-04-14 21:40:36 +01:00
  • cf252a8592 allow custom path for vad model Max Bain 2023-04-14 15:02:58 +01:00
  • 6a72b61564 clamp end_timestamp to prevent infinite loop m-bain 2023-04-11 20:15:37 +01:00
  • 48ed89834e Merge pull request #169 from invisprints/v2-opt-load-model m-bain 2023-04-09 13:39:13 +01:00
  • bb15c9428f opti the inference loop invisprints 2023-04-09 15:58:55 +08:00
  • 9482d324d0 Merge pull request #162 from dev-nomi/cli_argument_type m-bain 2023-04-05 13:40:04 -07:00
  • 4146e56d5b Added vad_filter type dev-nomi 2023-04-05 17:11:29 +05:00
  • 118e7deedb Merge pull request #161 from diasks2/fix_typo m-bain 2023-04-04 19:00:18 -07:00
  • 70a4a0a25c Fix typo Kevin Dias 2023-04-05 10:50:49 +09:00
  • 40948a3d00 fix whisper version to 20230314 for no breaking m-bain 2023-04-04 12:42:34 -07:00
  • c8be6ac94d update python example m-bain 2023-04-03 12:18:31 -07:00
  • a582a59493 mkdir for torch cache in case it doesnt exist m-bain 2023-04-01 13:05:40 -07:00
  • 861379edc3 Merge pull request #157 from Ryan5453/fix/whisper-req m-bain 2023-03-31 16:40:19 -07:00
  • 4af345434a Update requirements.txt Ryan 2023-03-31 19:36:38 -04:00
  • 634799b3be hf token only for diarization m-bain 2023-03-31 16:15:40 -07:00
  • 189aeac83e v2 lets goo Max Bain 2023-04-01 00:10:45 +01:00
  • bc2776017e v2 lets go Max Bain 2023-04-01 00:09:29 +01:00
  • 11a78d7ced handle tmp wav file better Max Bain 2023-04-01 00:06:40 +01:00