06d32bf0c1
Bump version to 1.0.0 ( #696 )
CI / run-tests (push) Failing after 1s
CI / check-code-format (push) Failing after 1s
CI / build-and-push-package (push) Has been skipped
2024-02-22 09:49:01 +01:00
30d6043e90
Prevent infinite loop for out-of-bound timestamps in clip_timestamps ( #697 )
...
Same as https://github.com/openai/whisper/pull/2005
2024-02-22 09:48:35 +01:00
22c75d0cc3
Update README.md ( #672 )
...
Add Faster-Whisper-Transcriber to community integrations.
2024-02-21 10:18:11 +01:00
092067208b
Add clip_timestamps and hallucination_silence_threshold options ( #646 )
2024-02-20 17:34:54 +01:00
6ffcbdfbc2
Fix typos in README.md ( #668 )
2024-02-20 17:33:17 +01:00
52695567c9
Bumps up PyAV version to support Python 3.12.x ( #679 )
2024-02-20 17:31:07 +01:00
c6b28ed3a0
Update README.md ( #685 )
...
I'm surprised that WhisperX hasn't made it into this list yet, as it has more stars than faster-whisper itself 🚀
2024-02-20 17:28:00 +01:00
4ab646035f
Upgrade ctranslate2 version to support CUDA 12 ( #694 )
2024-02-20 17:26:55 +01:00
f144e4c83d
Expands the note for distil-whisper ( #659 )
2024-01-28 21:48:40 +01:00
3aec421849
Add: More clarity of what "max_new_tokens" does ( #658 )
...
* Add: More clarity of what "max_new_tokens" does
2024-01-28 21:40:33 +01:00
64b9f244bd
Whisper-Streaming mention ( #656 )
...
under community integrations
2024-01-25 18:27:27 +01:00
00efce1696
Bugfix: Illogical "Avoid computing higher temperatures on no_speech" ( #652 )
2024-01-24 11:54:43 +01:00
ad3c83045b
support distil-whisper ( #557 )
2024-01-24 10:17:12 +01:00
72ff979a2e
Add GUI faster-whisper project README.md ( #554 )
...
Added aTrain GUI faster-whisper transcription and diarization tool as community project.
Co-authored-by: JuergenFleiss <118339672+Juergen-J-F@users.noreply.github.com >
2024-01-18 13:01:02 +01:00
615de0d2d9
add WhisperLive to community integration ( #647 )
2024-01-18 12:54:14 +01:00
44f7e58947
Update whisper-standalone-win description in README.md ( #508 )
...
* Update whisper-standalone-win description in README.md
2023-12-14 13:03:46 +01:00
ebcfd6b964
Fix broken prompt_reset_on_temperature ( #604 )
...
* Fix broken prompt_reset_on_temperature
Fixing: https://github.com/SYSTRAN/faster-whisper/issues/603
Broken because `generate_with_fallback()` doesn't return final temperature.
Regression since PR356 -> https://github.com/SYSTRAN/faster-whisper/pull/356
2023-12-13 13:14:39 +01:00
19329a3611
Word timing tweaks ( #616 )
2023-12-13 12:38:44 +01:00
65094b779e
Update info on cuBLAS and cuDNN libs in README.md ( #513 )
2023-11-27 12:12:47 +01:00
9641d5f56a
Force read-mode in av.open ( #566 )
...
The `av.open` functions checks input metadata to determine the mode to open with ("r" or "w"). If an input to `decode_audio` is found to be in write-mode, without this change it can't be read. Forcing read mode solves this.
2023-11-27 10:43:35 +01:00
e1a218fab1
Bump version to 0.10.0
CI / check-code-format (push) Failing after 1s
CI / run-tests (push) Failing after 1s
CI / build-and-push-package (push) Has been skipped
2023-11-24 23:19:47 +01:00
3084409633
Add V3 Support ( #578 )
...
* Add V3 Support
* update conversion example
---------
Co-authored-by: oscaarjs <oscar.johansson@conversy.se >
2023-11-24 23:16:12 +01:00
5a0541ea7d
Bump version to 0.9.0
CI / check-code-format (push) Failing after 0s
CI / run-tests (push) Failing after 0s
CI / build-and-push-package (push) Has been skipped
2023-09-18 16:21:37 +02:00
e94711bb5c
Add property WhisperModel.supported_languages ( #476 )
...
* Expose function supported_languages
* Make it a method
2023-09-14 17:42:02 +02:00
0048844f54
Expose function available_models ( #475 )
...
* Expose function available_models
* Add test case
2023-09-14 17:17:01 +02:00
a49097e655
Add some missing typing annotations in transcribe.py
2023-09-12 15:45:54 +02:00
81086f6d33
Always run the encoder at the beginning of the loop ( #468 )
2023-09-12 14:44:37 +02:00
f697945691
Update tokenizers requirement to include version 0.14 ( #469 )
2023-09-12 14:44:22 +02:00
727ab81f31
Improve error message for invalid task and language parameters ( #466 )
2023-09-12 10:02:23 +02:00
0285d46f6f
Add more details about the requirements in the README ( #463 )
2023-09-08 14:35:17 +02:00
ad388cd394
Bump version to 0.8.0
CI / check-code-format (push) Failing after 0s
CI / run-tests (push) Failing after 0s
CI / build-and-push-package (push) Has been skipped
2023-09-04 11:56:48 +02:00
4a41746e55
Log a warning when the model is English-only but the language is set to something else ( #454 )
2023-09-04 11:55:40 +02:00
1e6eb967c9
Add "large" alias for "large-v2" model ( #453 )
2023-09-04 11:54:42 +02:00
f0ff12965a
Expose generation parameter no_repeat_ngram_size ( #449 )
2023-09-01 17:31:30 +02:00
5871858a5f
Force the garbage collector to run after decoding the audio with PyAV ( #448 )
2023-09-01 15:25:13 +02:00
e87fbf8a49
Added audio duration after VAD to TranscriptionInfo object ( #445 )
...
* Added VAD removed audio duration to TranscriptionInfo object
Along with the duration of the original audio, this commit adds the seconds of audio removed by the VAD to the returned info obj
* Chaning naming for duration_after_vad
Instead of the property returning the audio duration removed, it now returns the final duration after the vad.
If vad_filter is False or if it doesn't remove any audio, the original duration is returned.
2023-08-31 17:19:48 +02:00
7b271da035
docs: add wscribe to community integrations ( #427 )
...
wscribe is a utility to generate transcript specifically to make it easy
for further manual edits accompanied by the wscribe-editor
2023-08-17 08:50:24 +02:00
1562b02345
added repetition_penalty to TranscriptionOptions ( #403 )
...
Co-authored-by: Aisu Wata <aisu.wata0@gmail.com >
2023-08-06 10:08:24 +02:00
1ce16652ee
Adds DEBUG log message for prompt_reset_on_temperature ( #399 )
...
Produce DEBUG log message if prompt_reset_on_temperature threshold is met.
2023-08-04 09:06:17 +02:00
857be6f621
Rename clear_previous_text_on_temperature argument ( #398 )
...
`prompt_reset_on_temperature` is more clear what it does.
2023-08-03 18:44:37 +02:00
1a1eb1a027
Add clear_previous_text_on_temperature parameter ( #397 )
...
* Add clear_previous_text_on_temperature parameter
* Add a description
2023-08-03 15:40:58 +02:00
5c17de1771
Bump version to 0.7.1
CI / check-code-format (push) Failing after 0s
CI / run-tests (push) Failing after 0s
CI / build-and-push-package (push) Has been skipped
2023-07-24 11:10:12 +02:00
0f55c436fe
Invalidate the cached encoder output when no_speech threshold is met ( #376 )
2023-07-24 10:57:15 +02:00
e786e26f75
Return result with best log prob when all temperature fallbacks failed ( #356 )
...
* Resolve Inference Selection Bug
* Refactor for better readability
* Filter out results with compression_ratio
* Refactor to avoid variable repetition
* Fix incorrect index and perform minor refactoring
* Remove final_temperature variable
2023-07-20 16:13:11 +02:00
687db319e0
Remove duplicate code ( #359 )
2023-07-18 16:03:01 +02:00
171d90dd1f
Bump version to 0.7.0
CI / check-code-format (push) Failing after 1s
CI / run-tests (push) Failing after 1s
CI / build-and-push-package (push) Has been skipped
2023-07-18 15:23:47 +02:00
0e051a5b77
Prepend prefix tokens with the initial timestamp token ( #358 )
2023-07-18 15:22:39 +02:00
2a37390fed
Minor reformatting in code snippet
2023-07-18 15:08:53 +02:00
3b4a6aa1c2
Improve timestamp heuristics ( #336 )
...
* Improve timestamp heuristics
* Chore
2023-07-05 15:16:53 +02:00
c7cb2aa8d4
Add support for using whisper models from Huggingface by specifying the model id. ( #334 )
...
* Add support for downloading CTranslate-converted models from Huggingface.
* Update utils.py to pass Flake8.
* Update utils.py to pass black.
* Remove redundant usage instructions.
* Apply suggestions from code review
Co-authored-by: Guillaume Klein <guillaumekln@users.noreply.github.com >
---------
Co-authored-by: Guillaume Klein <guillaumekln@users.noreply.github.com >
2023-07-03 17:40:10 +02:00
trungkienbkhn