Commit Graph

  • 12706adb7d
    Merge branch 'main' into main Jong Wook Kim 2023-03-06 18:54:59 -05:00
  • b80bcf610d
    apply formatting with black (#1038) Jong Wook Kim 2023-03-06 18:50:37 -05:00
  • 12410616f2 fix isort Jong Wook Kim 2023-03-06 15:41:41 -08:00
  • f4d7512cd9 add isort Jong Wook Kim 2023-03-06 15:23:38 -08:00
  • 4090900a26 add flake8 Jong Wook Kim 2023-03-06 15:05:13 -08:00
  • f8d94c6df6 applying black (with the default 88-column limit) Jong Wook Kim 2023-03-06 14:45:21 -08:00
  • 500d0fe966
    word-level timestamps in transcribe() (#869) Jong Wook Kim 2023-03-06 17:00:49 -05:00
  • 8cc58d35ef
    Merge 6cbcc2cff4fcce166e7d4a5038766bb38070c39f into eab8d920edf3947294c466f3912c24ed4b191264 Pikauba 2023-03-06 17:00:37 -05:00
  • 49193c599c
    Merge a99be390d78bac3138745d4889e82844851af452 into eab8d920edf3947294c466f3912c24ed4b191264 jhj0517 2023-03-06 16:59:32 -05:00
  • 2b079c41fa annotating that word_timestamps is experimental Jong Wook Kim 2023-03-06 13:31:55 -08:00
  • 145f325d68 fix merge error 2 Jong Wook Kim 2023-03-06 13:18:57 -08:00
  • 31cd418f27 fix merge error Jong Wook Kim 2023-03-06 13:13:22 -08:00
  • 6ed4c11d89
    Merge branch 'main' into word-level-timestamps Jong Wook Kim 2023-03-06 16:02:52 -05:00
  • eab8d920ed
    Decoding improvements (#1033) Jong Wook Kim 2023-03-06 14:32:32 -05:00
  • f042dcfa34 not ignoring the last segment ending with one timestamp Jong Wook Kim 2023-03-06 01:20:57 -08:00
  • bbd0d6f08e suppress task tokens (transcribe/translate) Jong Wook Kim 2023-03-06 00:42:42 -08:00
  • 7651e91c1e
    Merge fd0552b0c544eca88f623bbbd6ce50ff0b71a5df into 3e1780fd37686666f568be9c99f5b5e3e4f2eb92 m-bain 2023-03-04 05:29:22 +02:00
  • 9e53f52ca2
    Merge 545cd9a41f8a19333541a28890b97715c7c8766c into 3e1780fd37686666f568be9c99f5b5e3e4f2eb92 Isaac Slaughter 2023-03-04 05:29:19 +02:00
  • f7b7c8f6d7
    Merge 2dfecdc1207858934796b95391172313b6e40bcd into 3e1780fd37686666f568be9c99f5b5e3e4f2eb92 sanxfxteam 2023-03-04 05:29:18 +02:00
  • 3e1780fd37
    Update README.md (#894) Roman Vasilenko 2023-03-03 19:41:59 -05:00
  • 2e709a6a44
    Merge branch 'main' into patch-1 Jong Wook Kim 2023-03-03 19:39:29 -05:00
  • a99be390d7 added progress_callback in transcribe method Jhjoon05 2023-03-04 05:23:33 +09:00
  • c80f8ef809 added progress_callback in transcribe method Jhjoon05 2023-03-04 03:22:57 +09:00
  • 2f3e7fe944
    remove auxiliary audio extension Local State 2023-03-03 07:18:36 -05:00
  • 35fc151859
    Update tokenizer.py spgoswami1 2023-03-01 19:55:03 +05:30
  • 8e4d13abec
    Update transcribe.py spgoswami1 2023-03-01 19:45:08 +05:30
  • de0e44d60a
    Update tokenizer.py spgoswami1 2023-03-01 19:44:46 +05:30
  • 5147066cc7
    Update decoding.py spgoswami1 2023-03-01 19:44:26 +05:30
  • 22641e0931
    Update README.md spgoswami1 2023-03-01 19:43:46 +05:30
  • c47a6f0be3 Revert "edit requirments to enable cuda" Jhjoon05 2023-03-01 19:54:15 +09:00
  • f5c0c95a7b edit requirments to enable cuda Jhjoon05 2023-03-01 19:42:11 +09:00
  • c662ab0776 Revert "added requirements-cuda" Jhjoon05 2023-03-01 19:40:38 +09:00
  • 4d25b99548 added requirements-cuda Jhjoon05 2023-03-01 19:35:53 +09:00
  • 47c5120305 added progress callback Jhjoon05 2023-03-01 18:14:58 +09:00
  • 3f5f2971b6
    Update README.md Will 保哥 2023-02-28 00:17:31 +08:00
  • 48c3f614c1 condition_on_previous was being partially ignored since prompt_reset_since was being calculated before tokens from the current segment were added to all_tokens. Moved calculation to respect condition_on_previous. susan 2023-02-24 11:54:47 -08:00
  • 6cbcc2cff4 per token confidence added Antoine Dufour 2023-02-22 12:19:00 -05:00
  • 8eb29c3ef1
    Expose punctuation options in cli and transcribe() (#973) ryanheise 2023-02-17 06:59:40 +11:00
  • d0e16b3469 Expose punctuation options in cli and transcribe() Ryan Heise 2023-02-16 21:58:17 +11:00
  • c46cc347fd
    Update model-card.md KENTAR 2023-02-13 17:33:35 +01:00
  • 596cbb55ea improve the seek updating algorithm jumon 2023-02-07 16:01:08 +09:00
  • 48537aaf10 skip median filtering when the input is too small Jong Wook Kim 2023-02-02 09:34:55 -08:00
  • 5fa43566f0 miscellaneous improvements Jong Wook Kim 2023-02-02 01:28:10 -08:00
  • ff6cbfdf3b
    Merge branch 'main' into word-level-timestamps Jong Wook Kim 2023-02-02 04:04:18 -05:00
  • 7858aa9c08
    Fix infinite loop caused by incorrect timestamp tokens prediction (#914) Andrey Chernykh 2023-02-02 06:46:51 +07:00
  • 25d5ccc486
    Update decoding.py Jong Wook Kim 2023-02-01 15:44:48 -08:00
  • e5f3168f2f Fix infinite loop caused by incorrect timestamp tokens prediction Andrew Chernyh 2023-02-01 16:04:03 +07:00
  • 2dfecdc120 Reconfigure output to utf-8 sanxfxteam 2023-01-28 13:00:39 -08:00
  • 5c1a8c10e7
    clarify that 3.11 is not supported Jong Wook Kim 2023-01-27 00:01:49 -08:00
  • 1848b4127c
    Update README.md Roman Vasilenko 2023-01-25 11:34:56 -05:00
  • 6c431c41b1 find_alignment() function Jong Wook Kim 2023-01-25 00:19:25 -08:00
  • 8e2756bb1f loosen nvcc version match regex Jong Wook Kim 2023-01-24 21:18:39 -08:00
  • 040aa0444a
    Merge branch 'main' into word-level-timestamps Jong Wook Kim 2023-01-24 14:59:04 -08:00
  • d4f9399506 fix broken merge Jong Wook Kim 2023-01-24 14:58:51 -08:00
  • 4e635c6644
    Update README.md about Python 3.8+ requirement Jong Wook Kim 2023-01-24 14:45:56 -08:00
  • 89133bd1d3
    Merge branch 'main' into word-level-timestamps Jong Wook Kim 2023-01-24 14:19:02 -08:00
  • a6b36ede1f
    drop python 3.7 support (#889) Jong Wook Kim 2023-01-24 14:05:57 -08:00
  • 3944318a53 drop python 3.7 support Jong Wook Kim 2023-01-24 13:43:15 -08:00
  • 9f27dcdcd4
    Merge branch 'main' into add_confidence_score Emir Demirel 2023-01-24 23:42:30 +03:00
  • 08c5cdb40f adding word confidence score computation Emir Demirel 2023-01-24 23:41:49 +03:00
  • f64d8bc5a7
    Merge branch 'main' into word-level-timestamps Jong Wook Kim 2023-01-24 12:08:41 -08:00
  • cd5191fdcb installs an older version of Triton if CUDA < 11.4 Jong Wook Kim 2023-01-24 11:06:34 -08:00
  • 55f690af79 Release 20230124 v20230124 Jong Wook Kim 2023-01-24 11:11:08 -08:00
  • 812f44674e
    Merge branch 'main' into word-level-timestamps Jong Wook Kim 2023-01-24 10:25:35 -08:00
  • 7f1ef223ab
    handle printing even if sys.stdout.buffer is not available (#887) Jong Wook Kim 2023-01-24 10:12:04 -08:00
  • 4ee147ca59 handle printing even if sys.stdout.buffer is not available Jong Wook Kim 2023-01-24 10:07:23 -08:00
  • 8ce6277362 add scipy as dev dependency Jong Wook Kim 2023-01-24 09:34:46 -08:00
  • 54f2901a72 a simple word-level timestamps test Jong Wook Kim 2023-01-24 09:30:32 -08:00
  • b61e8f4fd1 triton implementation of median_filter Jong Wook Kim 2023-01-24 09:30:12 -08:00
  • 5d62c7bbf5
    Create Sasha Trailer SiobhanMcHugh 2023-01-24 16:59:06 +11:00
  • 1d2ed66d8d add test for dtw implementations Jong Wook Kim 2023-01-23 14:16:14 -08:00
  • 80331c0c67 triton implementation for dtw Jong Wook Kim 2023-01-23 11:40:37 -08:00
  • 545cd9a41f
    Merge branch 'main' into bound-timestamp Isaac Slaughter 2023-01-23 13:32:22 -05:00
  • fb12414f26
    Merge branch 'main' into word-level-timestamps Jong Wook Kim 2023-01-22 00:54:51 -08:00
  • f5bfe004ec
    Add TSV formatted output in transcript, using integer start/end times in milliseconds. (#228) Niels Mayer 2023-01-22 00:27:17 -08:00
  • 691ffc2315 docstring edit Jong Wook Kim 2023-01-22 00:21:48 -08:00
  • f7e96de964 fix syntax error Jong Wook Kim 2023-01-22 00:11:06 -08:00
  • b161f34d2d
    Merge branch 'main' into main Jong Wook Kim 2023-01-22 00:05:51 -08:00
  • da600abd2b
    Added --output_format option (#333) Aaryan YVS 2023-01-22 13:28:38 +05:30
  • dfea59cba7 refactor output format handling Jong Wook Kim 2023-01-21 23:53:47 -08:00
  • d8ba2f2741
    Merge branch 'main' into main Jong Wook Kim 2023-01-21 22:30:01 -08:00
  • 742d2f4c88 numba implementation for dtw, replacing dtw-python Jong Wook Kim 2023-01-21 16:07:37 -08:00
  • 8f878fa6fa
    Merge branch 'openai:main' into main Niels Mayer 2023-01-21 14:13:16 -08:00
  • cfd2b81804
    Merge branch 'main' into word-level-timestamps Jong Wook Kim 2023-01-21 01:48:02 -08:00
  • 46ea501da2 moving to timing.py Jong Wook Kim 2023-01-21 01:15:13 -08:00
  • 9f7aba6099
    Handle XDG_CACHE_HOME properly for download_root (#864) zer0-x 2023-01-21 12:09:39 +03:00
  • 48ee627846
    Merge branch 'main' into main Jong Wook Kim 2023-01-20 21:54:17 -08:00
  • 8f9357fa99 word-level timestamps in transcribe() Jong Wook Kim 2023-01-20 12:30:50 -08:00
  • 21569c3647
    Merge branch 'openai:main' into main Niels Mayer 2023-01-20 11:59:58 -08:00
  • 12e1089462
    use stdout for printing transcription progress (#867) Jong Wook Kim 2023-01-20 00:54:05 -08:00
  • 2311bd5122
    use stdout for printing transcription progress Jong Wook Kim 2023-01-20 00:52:09 -08:00
  • 38b9af7a86 Handle XDG_CACHE_HOME properly for download_root zer0-x 2023-01-19 22:35:14 +03:00
  • 51c785f7c9
    add another hasattr check for torch.backends.mps Jong Wook Kim 2023-01-18 14:44:02 -08:00
  • 4b77a81c1f
    hasattr check for torch.backends.mps Jong Wook Kim 2023-01-18 14:39:07 -08:00
  • 2c914999bd
    Merge branch 'main' into main Jong Wook Kim 2023-01-18 14:03:54 -08:00
  • ea1c266709
    Fix bug where mm is mistakenly replaced with hmm in e.g. 20mm (#659) Markus Hennerbichler 2023-01-18 18:41:11 +00:00
  • 5a15b0c319
    Merge branch 'main' into fix-mm-normalisation Jong Wook Kim 2023-01-18 10:31:01 -08:00
  • 8135a7c31c verbose outputs from pytest Jong Wook Kim 2023-01-18 10:30:18 -08:00
  • 532dd4c86c
    Merge branch 'main' into fix-mm-normalisation Jong Wook Kim 2023-01-18 10:19:15 -08:00
  • 9d646db9d8
    print '?' if a letter can't be encoded using the system default encoding (#859) Jong Wook Kim 2023-01-17 23:28:36 -08:00