Commit Graph

  • d32ec3e301 fix: add missing comma main Barabazs 2025-10-21 09:13:50 -06:00
  • db317c358b feat: add language-aware sentence tokenization (#1269) pplkit 2025-10-21 19:27:26 +05:30
  • 6e1d1caaf4 fix: incorrect type annotation in get_writer return value The audio_path attribute that the __call__ method of the ResultWriter class takes is a str, not TextIO JulianFP 2025-05-13 02:45:33 +02:00
  • c8f7597345 feat: add hotwords argument to CLI for improved recognition of rare terms Barabazs 2025-10-17 15:20:04 +00:00
  • 5925e5f8c7 docs: add cuDNN troubleshooting for common issues (#1266) Barabazs 2025-10-16 02:56:51 -06:00
  • 617835dc27 chore: upgrade torch and torchaudio dependencies to 2.8.0 v3.7.4 Barabazs 2025-10-16 07:41:45 +00:00
  • 92227e7412 fix: lock down torch and torchaudio versions (#1265) v3.7.3 Barabazs 2025-10-16 00:42:10 -06:00
  • 0fa81b31f1 feat: add Swedish alignment model (#1110) Paffe 2025-10-15 08:08:18 +02:00
  • 505bd9c0b5 chore: refine triton dependency to restrict installation to x86_64 Linux (#1259) v3.7.2 Barabazs 2025-10-12 02:38:29 -06:00
  • 895e5a8493 chore: update numpy dependency constraints for Python 3.13 compatibility (#1258) v3.7.1 Barabazs 2025-10-12 02:31:44 -06:00
  • a58ff9cb20 bump: update version to 3.7.0 v3.7.0 Barabazs 2025-10-10 07:37:17 +00:00
  • d13171cdde feat: add support for python 3.13 (#1256) Barabazs 2025-10-10 09:36:24 +02:00
  • c1c08c472f bump: update version to 3.6.0 v3.6.0 Barabazs 2025-10-10 06:45:00 +00:00
  • a51ae7a81a feat: add centralized logging to replace ad-hoc print statements (#1254) Barabazs 2025-10-10 08:41:06 +02:00
  • 3b1b9a8c4d refactor: rename types.py to schema.py to avoid stdlib conflict Barabazs 2025-10-09 12:22:58 +00:00
  • 027ec57aee doc: update cpu only example (#1164) Tomáš Hnyk 2025-10-09 09:34:54 +02:00
  • 64e307cc29 chore: remove redundant variable & improve load_model function documentation (#1197) 3manifold 2025-10-09 09:32:02 +02:00
  • 2663f2edb5 doc: fix diarize import in example script (#1192) Adrian Wan 2025-10-09 16:27:07 +09:00
  • c266ac5459 chore: update version to 3.5.0 v3.5.0 Barabazs 2025-10-08 09:24:25 +00:00
  • 95fecb91c8 build: upgrade PyTorch to 2.7.1 with CUDA 12.8 and multi-platform support Jim Chen 2025-10-08 17:21:28 +08:00
  • b1c8ac7de6 Change alignment model for Vietnamese language Nguyen Binh 2024-04-11 16:01:20 +02:00
  • bf150e442e feat: update Punkt tokenizer to use pre-trained model and handle missing data Barabazs 2025-10-02 16:06:38 +00:00
  • ed13dc8c6c recall.ai sponsor Max Bain 2025-10-03 00:12:53 +01:00
  • c7d31883bc Add jr, sr, and ph.d to punkt abbreviations Alex Cannan 2025-02-18 12:25:57 -05:00
  • 83afb81ac7 fix: restrict pyannote-audio version to avoid compatibility issues (#1242) v3.4.3 Barabazs 2025-10-01 08:37:00 +02:00
  • 2d9ce44329 fix(asr): load VAD model on correct CUDA device (#835) Jean Du 2025-07-02 14:07:59 +08:00
  • f4261f34e9 Remove unused code in Vad class 3manifold 2025-03-07 09:19:32 +01:00
  • 429658d4cc chore: bump version to 3.4.2 v3.4.2 Barabazs 2025-06-27 07:18:39 +00:00
  • e0833da5dc Fix: Ensure integer tensor indexing in get_wildcard_emission() Howard 2025-05-15 14:30:55 +08:00
  • ffedc5cdf0 fix: speaker embedding bug (#1178) v3.4.1 Barabazs 2025-06-25 13:55:20 +02:00
  • b93e9b6f57 chore: bump version to 3.4.0 v3.4.0 Barabazs 2025-06-24 14:18:02 +00:00
  • 844736e4e4 style: minor code formatting Barabazs 2025-06-24 12:58:40 +00:00
  • 220fec9aea refactor: update type hints in diarization module (PEP 585) Radu-Sebastian Amarie 2025-04-03 13:52:55 +00:00
  • 1631c3040f feat: enhance diarization with optional output of speaker embeddings Radu-Sebastian Amarie 2025-03-21 13:57:47 +00:00
  • d700b56c9c docs: add missing torch import to Python usage example in README Kirill 2025-06-07 23:36:49 +02:00
  • b343241253 feat: add diarize_model arg to CLI (#1101) bog 2025-05-31 13:32:31 +02:00
  • 6fe0a8784a docs: add troubleshooting section for libcudnn dependencies in README Barabazs 2025-05-31 11:19:36 +00:00
  • 5012650d0f chore: update lockfile Barabazs 2025-05-03 16:19:45 +02:00
  • 108bd0c400 chore: add lockfile check step to CI workflows Barabazs 2025-05-03 16:19:32 +02:00
  • b2d50a027b chore: bump version v3.3.4 Barabazs 2025-05-03 11:38:54 +02:00
  • 36d552cad3 fix: remove DiarizationPipeline from public API Barabazs 2025-05-02 13:04:24 +02:00
  • 7d36b832f9 refactor: update CLI entry point Barabazs 2025-05-01 14:19:42 +02:00
  • d2a493e910 refactor: implement lazy loading for module imports in whisperx Barabazs 2025-05-01 14:15:13 +02:00
  • f5b40b5366 chore: update version to 3.3.3 in pyproject.toml and uv.lock v3.3.3 Barabazs 2025-05-01 10:43:08 +02:00
  • ac0c8bd79a feat: add version and Python version arguments to CLI Barabazs 2025-05-01 10:43:02 +02:00
  • cd59f21d1a fix: downgrade ctranslate2 dependency version Barabazs 2025-05-01 09:54:19 +02:00
  • 0aed874589 Remove duplicated item Yan Cheng Cheok 2025-04-11 21:49:00 +08:00
  • 73db39703e chore: update GitHub Actions workflow to use dynamic ref for checkout v3.3.2 Barabazs 2025-04-10 09:34:24 +02:00
  • db1750fa48 chore: update ctranslate2 version requirement to >=4.5.0 Barabazs 2025-04-10 09:23:11 +02:00
  • f10dbf6ab1 fix: update setuptools configuration to include package discovery for whisperx Barabazs 2025-03-25 18:48:57 +01:00
  • a7564c2ad6 docs: update installation instructions Barabazs 2025-03-25 17:02:02 +01:00
  • e7712f496e refactor: update import statements to use explicit module paths across multiple files Barabazs 2025-03-25 16:13:55 +01:00
  • 8e53866704 feat: pass hotwords argument to get_prompt (#1073) jademlc 2025-03-24 10:47:47 +01:00
  • 3205436d58 Merge pull request #1002 from Barabazs/feat/uv Max Bain 2025-03-23 12:59:46 +00:00
  • 88939b9e8a Attempt to improve code clarity and modularity. improve-code google-labs-jules[bot] 2025-03-05 17:52:13 +00:00
  • 8c58c54635 Revert "feat: add Basque alignment model (#1074)" (#1077) Barabazs 2025-03-05 15:19:23 +01:00
  • 0d9807adc5 feat: add Basque alignment model (#1074) Xabi 2025-03-04 14:55:30 +01:00
  • 4db839018c feat: add Tagalog (tl - Filipino) Phoneme-based ASR Model (#1067) Amerogin Kamid 2025-02-23 16:59:48 +08:00
  • f8d11df727 docs: Update README example commands with generic audio path Barabazs 2025-02-19 08:24:04 +01:00
  • d2f0e53f71 chore: remove tmp workflow Barabazs 2025-01-17 08:03:59 +01:00
  • 7489ebf876 feat: update build and release workflow to use uv for package installation and publishing Barabazs 2025-01-16 08:38:17 +01:00
  • 90256cc481 feat: use uv recommended setup Barabazs 2025-01-16 08:21:45 +01:00
  • b41ebd4871 chore: add numpy to deps Barabazs 2025-01-16 08:16:46 +01:00
  • 63bc1903c1 feat: update Python compatibility workflow to use uv Barabazs 2025-01-16 08:10:22 +01:00
  • 272714e07d feat: use uv for building package Barabazs 2025-01-16 08:09:57 +01:00
  • 44e8bf5bb6 Merge pull request #1024 from philmcmahon/local-files-only-param Max Bain 2025-01-27 14:26:19 +00:00
  • 7b3c9ce629 Add models_cache_only param philmcmahon 2025-01-27 12:16:37 +00:00
  • 36d2622e27 feat: add Latvian align model Reinis Ivanovs 2025-01-24 22:24:15 +02:00
  • 8bfa12193b Merge pull request #1006 from tan90xx/main Max Bain 2025-01-20 14:05:34 +00:00
  • acbeba6057 Update silero.py tan90xx 2025-01-20 20:01:21 +08:00
  • fca563a782 Update silero.py tan90xx 2025-01-20 19:52:37 +08:00
  • 2117909bf6 Merge pull request #1005 from tan90xx/main Max Bain 2025-01-19 13:51:34 +00:00
  • de0d8fe313 chore: handle empty segments_list case in silero tan90xx 2025-01-19 21:20:56 +08:00
  • 355f8e06f7 Merge pull request #1003 from Barabazs/chore/remove-aws-url Max Bain 2025-01-17 15:28:24 +00:00
  • 86e2b3ee74 chore: remove deprecated VAD_SEGMENTATION_URL Barabazs 2025-01-17 09:12:05 +01:00
  • 70c639cdb5 doc: refer to DEFAULT_ALIGN_MODELS_HF for other langs Barabazs 2025-01-17 08:46:38 +01:00
  • 235536e28d Update links to language models in README Markus Jochim 2024-03-25 16:50:58 +01:00
  • 12604a48ea Merge pull request #986 from bfs18/main Max Bain 2025-01-14 21:03:51 +00:00
  • ffbc73664c change the docstrings and comments to English liupeng 2025-01-13 22:56:48 +08:00
  • 289eadfc76 fix a merge error. liupeng 2025-01-13 20:26:27 +08:00
  • 22a93f2932 Merge branch 'main' into main bfs18 2025-01-13 19:34:21 +08:00
  • 1027367b79 Merge pull request #995 from winking324/main Max Bain 2025-01-13 10:10:29 +00:00
  • 5e54b872a9 Merge branch 'main' into main Max Bain 2025-01-13 10:09:20 +00:00
  • 6be02cccfa Update asr.py Max Bain 2025-01-13 10:08:09 +00:00
  • 2f93e029c7 feat: add SegmentData type for temporary processing during alignment Barabazs 2025-01-13 09:27:33 +01:00
  • 024bc8481b refactor: consolidate segment data handling in alignment function Barabazs 2025-01-13 09:13:30 +01:00
  • f286e7f3de refactor: improve type hints and clean up imports Barabazs 2025-01-13 08:28:27 +01:00
  • 73e644559d refactor: remove namespace for consistency Barabazs 2025-01-13 08:26:49 +01:00
  • 1ec527375a fix vad_method is none winking324 2025-01-13 13:53:35 +08:00
  • 6695426a85 fix new vad paths Max Bain 2025-01-12 12:50:15 +00:00
  • 7a98456321 Merge pull request #888 from 3manifold/silero-vad Max Bain 2025-01-11 17:15:27 +00:00
  • aaddb83aa5 switch from case to ifelse Max Bain 2025-01-11 17:11:21 +00:00
  • c288f4812a Merge branch 'main' into silero-vad Max Bain 2025-01-11 17:05:53 +00:00
  • 4ebfb078c5 make no beam consistent with backtrack. liupeng 2025-01-09 23:13:11 +08:00
  • 65b2332e13 make align a bit faster. liupeng 2025-01-09 19:33:26 +08:00
  • 69281f3a29 support timestamps for numbers. liupeng 2025-01-09 15:23:40 +08:00
  • 734084cdf6 bump: update version to 3.3.1 v3.3.1 Barabazs 2025-01-08 18:00:34 +01:00
  • 9395b0de18 Update tmp.yml Barabazs 2025-01-07 08:11:47 +01:00
  • d57f9dc54c Create tmp.yml Barabazs 2025-01-07 08:06:59 +01:00
  • a90bd1ce3f dataclasses replace method justintennenbaum 2025-01-07 12:35:41 -05:00