whisperx

What's Changed

• fix: pin torchvision and torchcodec for torch 2.8 compatibility by @Barabazs in https://github.com/m-bain/whisperX/pull/1397

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.8.4...v3.8.5

What's Changed

• feat: add progress_callback to transcribe, align, and diarize by @Barabazs in https://github.com/m-bain/whisperX/pull/1371
• fix: remove dead model_bytes read that leaked file handle by @Barabazs in https://github.com/m-bain/whisperX/pull/1381
• fix: restore word-level timestamps for unalignable characters by @Barabazs in https://github.com/m-bain/whisperX/pull/1386
• fix: require faster-whisper>=1.2.0 for use_auth_token support (#1385) by @Barabazs in https://github.com/m-bain/whisperX/pull/1388

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.8.2...v3.8.4

What's Changed

• feat: expose avg_logprob per segment from ctranslate2 beam search by @Barabazs in https://github.com/m-bain/whisperX/pull/1350
• fix: revert #986 wildcard alignment that broke word-level timestamps (#1220) by @Barabazs in https://github.com/m-bain/whisperX/pull/1367

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.8.1...v3.8.2

What's Changed

• Fix: Respect --model_dir and --model_cache_only during alignment by @MrPrayer in https://github.com/m-bain/whisperX/pull/1285
• feat: forward --hf_token to WhisperModel for gated/private model support by @Barabazs in https://github.com/m-bain/whisperX/pull/1351

New Contributors

• @MrPrayer made their first contribution in https://github.com/m-bain/whisperX/pull/1285

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.8.0...v3.8.1

What's Changed

• feat: migrate to pyannote-audio v4 with speaker-diarization-community-1 by @Barabazs in https://github.com/m-bain/whisperX/pull/1349

Special thanks to @borgoat for taking the lead.

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.7.7...v3.8.0

Backport of word-level timestamp fixes from v3.8.4.

Bug Fixes

• Restore timestamps for unalignable characters (39aa9f5): Words containing digits, symbols, or foreign script (e.g. 4,9, £13.60) now get proper timestamps via a wildcard emission column. The previous patch (v3.X.Y) reverted PR #986 which removed wildcard support entirely. Fixes #1372.

Testing

• Add regression test for #1372 (da072d6)
• Add pytest dev dependency and CI test workflow (f9a3f8f)

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.7.8...v3.7.9

Backport of word-level timestamp fixes from v3.8.2.

Bug Fixes

• Restore original CTC forced-alignment (f2609a6): PR #986 caused all words to anchor to the start of the segment window (silence) instead of actual speech. Reverts get_trellis/backtrack to the original PyTorch tutorial implementation. Fixes #1220.
• Fix blank_id hardcoded to 0 (636f298): Broke alignment for HuggingFace models where blank is [pad], not index 0.

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.7.7...v3.7.8

What's Changed

• Optimize assign_word_speakers with interval tree for 228x speedup by @Mr-Neutr0n in https://github.com/m-bain/whisperX/pull/1338
• fix: pass no_repeat_ngram_size and repetition_penalty to CTranslate2 generate() by @RickSanchez93 in https://github.com/m-bain/whisperX/pull/1340
• chore: update type hints by @1carlito in https://github.com/m-bain/whisperX/pull/1342 and https://github.com/m-bain/whisperX/pull/1343
• fix: derive SRT/VTT cue times from word-level timestamps by @Barabazs in https://github.com/m-bain/whisperX/pull/1347

New Contributors

• @Mr-Neutr0n made their first contribution in https://github.com/m-bain/whisperX/pull/1338
• @RickSanchez93 made their first contribution in https://github.com/m-bain/whisperX/pull/1340
• @1carlito made their first contribution in https://github.com/m-bain/whisperX/pull/1342

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.7.6...v3.7.7

What's Changed

• chore: drop python 3.9 support by @Barabazs in https://github.com/m-bain/whisperX/pull/1328

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.7.5...v3.7.6

What's Changed

• docs: add cuDNN troubleshooting for common issues by @Barabazs in https://github.com/m-bain/whisperX/pull/1266
• feat: add hotwords argument to CLI for improved recognition of rare terms by @Barabazs in https://github.com/m-bain/whisperX/pull/1268
• Fix incorrect type annotations in get_writer function in utils.py by @JulianFP in https://github.com/m-bain/whisperX/pull/1144
• [1246] feat: added language-aware sentence tokenization by @pplkit in https://github.com/m-bain/whisperX/pull/1269
• fix: pin huggingface-hub<1.0.0 for pyannote-audio compatibility by @Barabazs in https://github.com/m-bain/whisperX/pull/1327

New Contributors

• @JulianFP made their first contribution in https://github.com/m-bain/whisperX/pull/1144
• @pplkit made their first contribution in https://github.com/m-bain/whisperX/pull/1269

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.7.4...v3.7.5

chore: upgrade torch and torchaudio dependencies to 2.8.0

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.7.3...v3.7.4

What's Changed

• feat: add Swedish alignment model by @Npahlfer in https://github.com/m-bain/whisperX/pull/1110
• fix: lock down torch and torchaudio versions by @Barabazs in https://github.com/m-bain/whisperX/pull/1265

New Contributors

• @Npahlfer made their first contribution in https://github.com/m-bain/whisperX/pull/1110

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.7.2...v3.7.3

What's Changed

• chore: refine triton dependency to restrict installation to x86_64 Linux by @Barabazs in https://github.com/m-bain/whisperX/pull/1259

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.7.1...v3.7.2

What's Changed

• chore: update numpy dependency constraints for Python 3.13 compatibility by @Barabazs in https://github.com/m-bain/whisperX/pull/1258

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.7.0...v3.7.1

What's Changed

• feat: add support for python 3.13 by @Barabazs in https://github.com/m-bain/whisperX/pull/1256

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.6.0...v3.7.0

Backport of word-level timestamp fixes from v3.8.4.

Bug Fixes

• Restore timestamps for unalignable characters (39aa9f5): Words containing digits, symbols, or foreign script (e.g. 4,9, £13.60) now get proper timestamps via a wildcard emission column. The previous patch (v3.X.Y) reverted PR #986 which removed wildcard support entirely. Fixes #1372.

Testing

• Add regression test for #1372 (da072d6)
• Add pytest dev dependency and CI test workflow (f9a3f8f)

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.6.1...v3.6.2

Backport of word-level timestamp fixes from v3.8.2.

Bug Fixes

• Restore original CTC forced-alignment (f2609a6): PR #986 caused all words to anchor to the start of the segment window (silence) instead of actual speech. Reverts get_trellis/backtrack to the original PyTorch tutorial implementation. Fixes #1220.
• Fix blank_id hardcoded to 0 (636f298): Broke alignment for HuggingFace models where blank is [pad], not index 0.

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.6.0...v3.6.1

What's Changed

• Update README.md to fix diarize code by @awan1 in https://github.com/m-bain/whisperX/pull/1192
• Remove redundant variable & improve load_model function documentation by @3manifold in https://github.com/m-bain/whisperX/pull/1197
• Update README.md to include --device cpu by @felagund in https://github.com/m-bain/whisperX/pull/1164
• refactor: rename types.py to schema.py to avoid stdlib conflict by @Barabazs in https://github.com/m-bain/whisperX/pull/1252
• feat: add centralized logging to replace ad-hoc print statements by @Barabazs in https://github.com/m-bain/whisperX/pull/1254

New Contributors

• @awan1 made their first contribution in https://github.com/m-bain/whisperX/pull/1192
• @felagund made their first contribution in https://github.com/m-bain/whisperX/pull/1164

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.5.0...v3.6.0

Backport of word-level timestamp fixes from v3.8.4.

Bug Fixes

• Restore timestamps for unalignable characters (39aa9f5): Words containing digits, symbols, or foreign script (e.g. 4,9, £13.60) now get proper timestamps via a wildcard emission column. The previous patch (v3.X.Y) reverted PR #986 which removed wildcard support entirely. Fixes #1372.

Testing

• Add regression test for #1372 (da072d6)
• Add pytest dev dependency and CI test workflow (f9a3f8f)

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.5.1...v3.5.2

Backport of word-level timestamp fixes from v3.8.2.

Bug Fixes

• Restore original CTC forced-alignment (f2609a6): PR #986 caused all words to anchor to the start of the segment window (silence) instead of actual speech. Reverts get_trellis/backtrack to the original PyTorch tutorial implementation. Fixes #1220.
• Fix blank_id hardcoded to 0 (636f298): Broke alignment for HuggingFace models where blank is [pad], not index 0.

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.5.0...v3.5.1

What's Changed

• Add jr, sr, and ph.d to punkt abbreviations by @alexcannan in https://github.com/m-bain/whisperX/pull/1053
• feat: use pre-trained Punkt model instead of empty parameters by @Barabazs in https://github.com/m-bain/whisperX/pull/1245
• Change the alignment model for Vietnamese language by @nguyenvulebinh in https://github.com/m-bain/whisperX/pull/776
• build: bump torch to 2.7.1 and CUDA 12.8 support by @jim60105 in https://github.com/m-bain/whisperX/pull/1182

New Contributors

• @alexcannan made their first contribution in https://github.com/m-bain/whisperX/pull/1053
• @nguyenvulebinh made their first contribution in https://github.com/m-bain/whisperX/pull/776

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.4.3...v3.5.0

Backport of word-level timestamp fixes from v3.8.4.

Bug Fixes

• Restore timestamps for unalignable characters (39aa9f5): Words containing digits, symbols, or foreign script (e.g. 4,9, £13.60) now get proper timestamps via a wildcard emission column. The previous patch (v3.X.Y) reverted PR #986 which removed wildcard support entirely. Fixes #1372.

Testing

• Add regression test for #1372 (da072d6)
• Add pytest dev dependency and CI test workflow (f9a3f8f)

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.4.4...v3.4.5

Backport of word-level timestamp fixes from v3.8.2.

Bug Fixes

• Restore original CTC forced-alignment (f2609a6): PR #986 caused all words to anchor to the start of the segment window (silence) instead of actual speech. Reverts get_trellis/backtrack to the original PyTorch tutorial implementation. Fixes #1220.
• Fix blank_id hardcoded to 0 (636f298): Broke alignment for HuggingFace models where blank is [pad], not index 0.

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.4.3...v3.4.4

What's Changed

• Remove unused code in Vad class by @3manifold in https://github.com/m-bain/whisperX/pull/1079
• fix vad model load bug. by @duj12 in https://github.com/m-bain/whisperX/pull/835
• fix: restrict pyannote-audio version to avoid compatibility issues by @Barabazs in https://github.com/m-bain/whisperX/pull/1242

New Contributors

• @duj12 made their first contribution in https://github.com/m-bain/whisperX/pull/835

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.4.2...v3.4.3

What's Changed

• Fix: Ensure integer tensor indexing in get_wildcard_emission() to avoid IndexError by @HowardWhile in https://github.com/m-bain/whisperX/pull/1146

New Contributors

• @HowardWhile made their first contribution in https://github.com/m-bain/whisperX/pull/1146

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.4.1...v3.4.2

What's Changed

• fix: speaker embedding bug by @Barabazs in https://github.com/m-bain/whisperX/pull/1178

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.4.0...v3.4.1

What's Changed

• chore: add lockfile check step to CI workflows by @Barabazs in https://github.com/m-bain/whisperX/pull/1130
• docs: add common issue section for libcudnn dependencies in README by @Barabazs in https://github.com/m-bain/whisperX/pull/1161
• feat: diarization model env config by @bgdnvk in https://github.com/m-bain/whisperX/pull/1101
• docs: add missing torch import to Python usage example in README by @hammerill in https://github.com/m-bain/whisperX/pull/1168
• feat: enhance diarization with optional output of speaker embeddings by @eek in https://github.com/m-bain/whisperX/pull/1085

New Contributors

• @bgdnvk made their first contribution in https://github.com/m-bain/whisperX/pull/1101
• @hammerill made their first contribution in https://github.com/m-bain/whisperX/pull/1168
• @eek made their first contribution in https://github.com/m-bain/whisperX/pull/1085

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.3.4...v3.4.0

Backport of word-level timestamp fixes from v3.8.4.

Bug Fixes

• Restore timestamps for unalignable characters (39aa9f5): Words containing digits, symbols, or foreign script (e.g. 4,9, £13.60) now get proper timestamps via a wildcard emission column. The previous patch reverted PR #986 which removed wildcard support entirely. Fixes #1372.

Testing

• Add regression test for #1372 (da072d6)
• Add pytest dev dependency and CI test workflow (f9a3f8f)

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.3.5...v3.3.6

Backport of word-level timestamp fixes from v3.8.2.

Bug Fixes

• Restore original CTC forced-alignment (f2609a6): PR #986 caused all words to anchor to the start of the segment window (silence) instead of actual speech. Reverts get_trellis/backtrack to the original PyTorch tutorial implementation. Fixes #1220.
• Fix blank_id hardcoded to 0 (636f298): Broke alignment for HuggingFace models where blank is [pad], not index 0.

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.3.4...v3.3.5

What's Changed

• feat: improve CLI loading speed by lazy loading public API by @Barabazs in https://github.com/m-bain/whisperX/pull/1128

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.3.3...v3.3.4

What's Changed

• Silero VAD support by @3manifold in https://github.com/m-bain/whisperX/pull/888
• refactor: add more types by @Barabazs in https://github.com/m-bain/whisperX/pull/996
• fix vad_method is none by @winking324 in https://github.com/m-bain/whisperX/pull/995
• support timestamp for numbers. by @bfs18 in https://github.com/m-bain/whisperX/pull/986
• Update links to language models in README by @MJochim in https://github.com/m-bain/whisperX/pull/757
• chore: remove deprecated VAD_SEGMENTATION_URL by @Barabazs in https://github.com/m-bain/whisperX/pull/1003
• chore: handle empty segments_list case in silero by @tan90xx in https://github.com/m-bain/whisperX/pull/1005
• chore: fix variable naming inconsistency from segments to segments_list by @tan90xx in https://github.com/m-bain/whisperX/pull/1006
• feat: add Latvian align model by @slikts in https://github.com/m-bain/whisperX/pull/1017
• Add models_cache_only param by @philmcmahon in https://github.com/m-bain/whisperX/pull/1024
• Added Phoneme-Based ASR Model for Tagalog by @mtfugin in https://github.com/m-bain/whisperX/pull/1067
• Basque alignment model by @xezpeleta in https://github.com/m-bain/whisperX/pull/1074
• Revert "feat: add Basque alignment model (#1074)" by @Barabazs in https://github.com/m-bain/whisperX/pull/1077
• feat: use uv for package/project management by @Barabazs in https://github.com/m-bain/whisperX/pull/1002
• feat(hotwords): Pass hotwords option to faster-whisper by @jademlc in https://github.com/m-bain/whisperX/pull/1073
• refactor: update import statements to use explicit module paths by @Barabazs in https://github.com/m-bain/whisperX/pull/1091
• docs: update installation instructions by @Barabazs in https://github.com/m-bain/whisperX/pull/1092
• fix: update setuptools configuration to include package discovery by @Barabazs in https://github.com/m-bain/whisperX/pull/1093
• Remove duplicated item by @yccheok in https://github.com/m-bain/whisperX/pull/1109
• fix: resolve dependency issues by @Barabazs in https://github.com/m-bain/whisperX/pull/1126

New Contributors

• @3manifold made their first contribution in https://github.com/m-bain/whisperX/pull/888
• @winking324 made their first contribution in https://github.com/m-bain/whisperX/pull/995
• @bfs18 made their first contribution in https://github.com/m-bain/whisperX/pull/986
• @MJochim made their first contribution in https://github.com/m-bain/whisperX/pull/757
• @tan90xx made their first contribution in https://github.com/m-bain/whisperX/pull/1005
• @slikts made their first contribution in https://github.com/m-bain/whisperX/pull/1017
• @philmcmahon made their first contribution in https://github.com/m-bain/whisperX/pull/1024
• @mtfugin made their first contribution in https://github.com/m-bain/whisperX/pull/1067
• @xezpeleta made their first contribution in https://github.com/m-bain/whisperX/pull/1074
• @jademlc made their first contribution in https://github.com/m-bain/whisperX/pull/1073
• @yccheok made their first contribution in https://github.com/m-bain/whisperX/pull/1109

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.3.1...v3.3.3

What's Changed

• chore: update ctranslate2 version requirement to >=4.5.0

This patch release should resolve CUDNN related issues.

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.3.1...v3.3.2

What's Changed

• refactor: add type hints and fix import statement by @Barabazs in https://github.com/m-bain/whisperX/pull/975
• feat: include speaker information in WriteTXT when diarizing by @Barabazs in https://github.com/m-bain/whisperX/pull/976
• Bug Fix: Suppress Numerals dataclasses replace method by @jmt0221 in https://github.com/m-bain/whisperX/pull/981

New Contributors

• @jmt0221 made their first contribution in https://github.com/m-bain/whisperX/pull/981

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.3.0...v3.3.1

What's Changed

• Update faster-whisper to 1.0.2 to enable model distil-large-v3 by @moritzbrantner in https://github.com/m-bain/whisperX/pull/814
• latest faster-whisper support added by @Hasan-Naseer in https://github.com/m-bain/whisperX/pull/875
• Working version with pyannote:3.3.2 and faster-whisper:1.1.0 by @ibombonato in https://github.com/m-bain/whisperX/pull/936
• Add ultization to verbose flag by @H4CK3Rabhi in https://github.com/m-bain/whisperX/pull/759
• Added local_files_only option on whisperx.load_model for offline mode by @RoqueGio in https://github.com/m-bain/whisperX/pull/867
• adding cache_dir to wav2vec2 by @bnitsan in https://github.com/m-bain/whisperX/pull/681
• feat: add basic installation test flow & restrict python versions by @Barabazs in https://github.com/m-bain/whisperX/pull/965
• chore: add build and release workflow by @Barabazs in https://github.com/m-bain/whisperX/pull/966
• fix: update README image source and enhance setup.py for long description by @Barabazs in https://github.com/m-bain/whisperX/pull/968
• docs: update installation instructions in README by @Barabazs in https://github.com/m-bain/whisperX/pull/969
• fix: add UTF-8 encoding when reading README.md by @xigh in https://github.com/m-bain/whisperX/pull/970
• chore: loosen ctranslate2 version restriction & bump whisperX version by @Barabazs in https://github.com/m-bain/whisperX/pull/971

New Contributors

• @moritzbrantner made their first contribution in https://github.com/m-bain/whisperX/pull/814
• @Hasan-Naseer made their first contribution in https://github.com/m-bain/whisperX/pull/875
• @ibombonato made their first contribution in https://github.com/m-bain/whisperX/pull/936
• @H4CK3Rabhi made their first contribution in https://github.com/m-bain/whisperX/pull/759
• @RoqueGio made their first contribution in https://github.com/m-bain/whisperX/pull/867
• @bnitsan made their first contribution in https://github.com/m-bain/whisperX/pull/681
• @xigh made their first contribution in https://github.com/m-bain/whisperX/pull/970

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.2.0...v3.3.0

Device and Language Support

• added Korean wav2vec2 model by @Boulaouaney in https://github.com/m-bain/whisperX/pull/277
• Add Czech alignment model by @Thebys in https://github.com/m-bain/whisperX/pull/280
• Adding Norwegian Bokmål and Norwegian Nynorsk by @peregilk in https://github.com/m-bain/whisperX/pull/636
• Support language names in --language parameter. by @jkukul in https://github.com/m-bain/whisperX/pull/517
• Add align model for catalan language. by @davidmartinrius in https://github.com/m-bain/whisperX/pull/581
• add missing Cantonese in supported languages by @MahmoudAshraf97 in https://github.com/m-bain/whisperX/pull/617
• Add alignment model for Malayalam by @kurianbenoy in https://github.com/m-bain/whisperX/pull/585
• Added Romanian phoneme-based ASR model by @Majdoddin in https://github.com/m-bain/whisperX/pull/791
• added alignment for sk and sl languages by @jan-panoch in https://github.com/m-bain/whisperX/pull/852
• Add war2vec model for Vietnamese in https://github.com/m-bain/whisperX/pull/278
• Add Urdu model support for alignment by @abCods in https://github.com/m-bain/whisperX/pull/374
• chore(writer): Join words without spaces for ja, zh by @jim60105 in https://github.com/m-bain/whisperX/pull/440

Bug Fixes and Stability Improvements

• fix Unequal Stack Size VAD error by @m-bain in https://github.com/m-bain/whisperX/pull/281
• fix: Bug in type hinting by @VisionOra in https://github.com/m-bain/whisperX/pull/294
• pin faster whisper by @sorgfresser in https://github.com/m-bain/whisperX/pull/474
• Fix repeat transcription on different languages and proper suppress_numerals use by @Joemgu7 in https://github.com/m-bain/whisperX/pull/395
• fix writer fail on segments 0 by @sorgfresser in https://github.com/m-bain/whisperX/pull/429
• fix missing speaker prefix by @invisprints in https://github.com/m-bain/whisperX/pull/438
• fix: correct defaut_asr_options with new options (patch 0.8) by @remic33 in https://github.com/m-bain/whisperX/pull/458
• Fixes --model_dir path by @canoalberto in https://github.com/m-bain/whisperX/pull/648
• fix: force ctranslate to version 4.4.0 by @Barabazs in https://github.com/m-bain/whisperX/pull/946
• fix: update faster-whisper dependencies by @cococig in https://github.com/m-bain/whisperX/pull/716
• fix: ZeroDivisionError when --print_progress True by @mvoggu in https://github.com/m-bain/whisperX/pull/494
• Minor fixes for word options and subtitles by @amolinasalazar in https://github.com/m-bain/whisperX/pull/549
• fix unboundlocalerror by @sorgfresser in https://github.com/m-bain/whisperX/pull/554
• Fix: Allow vad options to be configurable by passing to FasterWhisperPipeline and merge_chunks. by @abettke in https://github.com/m-bain/whisperX/pull/507
• fix minimum input length for torch wav2vec2 models by @MahmoudAshraf97 in https://github.com/m-bain/whisperX/pull/510
• fix(diarize): key error on empty track by @characat0 in https://github.com/m-bain/whisperX/pull/518
• pip compliance for git+ installs by @spbisc97 in https://github.com/m-bain/whisperX/pull/603

Documentation Updates

• adds link to whisperX medium on replicate.com by @CaRniFeXeR in https://github.com/m-bain/whisperX/pull/431
• Document --compute_type command line option by @dotgrid in https://github.com/m-bain/whisperX/pull/430
• adding link to Replicate demo by @daanelson in https://github.com/m-bain/whisperX/pull/352
• fix: typo in error message by @zamoshchin in https://github.com/m-bain/whisperX/pull/493
• Fix link in README.md by @jimregan in https://github.com/m-bain/whisperX/pull/668
• Update README.md by @valentt in https://github.com/m-bain/whisperX/pull/509
• Add a special note about Speaker-Diarization-3.0 in readme by @kaihe-stori in https://github.com/m-bain/whisperX/pull/521
• Update README to correct speaker diarization version link by @gillens in https://github.com/m-bain/whisperX/pull/618
• Update README.md by @mlopsengr in https://github.com/m-bain/whisperX/pull/630
• fix link by @M0HID in https://github.com/m-bain/whisperX/pull/605
• Remove torchvision from README by @baer in https://github.com/m-bain/whisperX/pull/378

Miscellaneous Changes

• move model to assets by @m-bain in https://github.com/m-bain/whisperX/pull/945
• Update alignment.py by @Ayushi-Desynova in https://github.com/m-bain/whisperX/pull/418
• Update alignment.py by @awerks in https://github.com/m-bain/whisperX/pull/427
• push contributions from main by @m-bain in https://github.com/m-bain/whisperX/pull/290
• make diarization faster by @davidas1 in https://github.com/m-bain/whisperX/pull/400
• Add device_index option by @sorgfresser in https://github.com/m-bain/whisperX/pull/266
• Add transcribe keywords by @sorgfresser in https://github.com/m-bain/whisperX/pull/269
• Added download path parameter. by @prameshbajra in https://github.com/m-bain/whisperX/pull/284
• Suppress numerals by @m-bain in https://github.com/m-bain/whisperX/pull/303
• Add Audacity export by @Ca-ressemble-a-du-fake in https://github.com/m-bain/whisperX/pull/309
• Update transcribe.py -> small change in batch_size description by @mabergerx in https://github.com/m-bain/whisperX/pull/382
• Suggest using pytorch-cuda 11.8 instead of 11.7 by @tijszwinkels in https://github.com/m-bain/whisperX/pull/255
• feat: Add merge chunks chunk_size as arguments. by @jim60105 in https://github.com/m-bain/whisperX/pull/445
• A solution to long subtitles and words without timestamps by @awerks in https://github.com/m-bain/whisperX/pull/459
• chore(writer): improve text display(ja etc) in json file by @darwintree in https://github.com/m-bain/whisperX/pull/472
• add faster whisper threading by @sorgfresser in https://github.com/m-bain/whisperX/pull/473
• Pyannote3 by @remic33 in https://github.com/m-bain/whisperX/pull/492
• Update alignment.py by @piuy11 in https://github.com/m-bain/whisperX/pull/487
• Pass patience and beam_size to faster-whisper. by @jkukul in https://github.com/m-bain/whisperX/pull/527
• remove the minimum length for alignment and print the failing segment by @MahmoudAshraf97 in https://github.com/m-bain/whisperX/pull/529
• Update setup.py to use pyannote.audio version with working GPU by @wuurrd in https://github.com/m-bain/whisperX/pull/531
• Update setup.py to download pyannote depending on platform by @justinwlin in https://github.com/m-bain/whisperX/pull/541
• Drop ffmpeg-python dependency and call ffmpeg directly. by @hidenori-endo in https://github.com/m-bain/whisperX/pull/570
• no align based on space by @sorgfresser in https://github.com/m-bain/whisperX/pull/556
• Update asr.py and make the model parameter be used by @kaka1909 in https://github.com/m-bain/whisperX/pull/580
• Move load_model after WhisperModel by @DougTrajano in https://github.com/m-bain/whisperX/pull/584
• Update pyannote to 3.1.0 by @remic33 in https://github.com/m-bain/whisperX/pull/586
• support for large-v3 by @MahmoudAshraf97 in https://github.com/m-bain/whisperX/pull/599
• Added option to load Custom VAD model to load model method by @Swami-Abhinav in https://github.com/m-bain/whisperX/pull/654
• Update pyannote to v3.1.1 to fix a diarization problem (and diarize.py) by @santialferez in https://github.com/m-bain/whisperX/pull/646
• Get rid of numeral_symbol_tokens variable in printed message by @KossaiSbai in https://github.com/m-bain/whisperX/pull/669
• Add Replicate large-v3 demo by @victor-upmeet in https://github.com/m-bain/whisperX/pull/703
• local vad model by @m-bain in https://github.com/m-bain/whisperX/pull/944
• Feat: add new align models - SHORT by @Equipo45 in https://github.com/m-bain/whisperX/pull/922
• Update alignment.py by @peregilk in https://github.com/m-bain/whisperX/pull/687

Full Changelog: https://github.com/m-bain/whisperX/compare/v3.1.1...v3.2.0

• translate functionality added
• fix word timestamp bug (words no longer have consecutive timestamps)