heimoshuiyu/faster-whisper
1
0
Fork 0
Code Issues Pull Requests 1 Packages Projects Releases Wiki Activity
182 Commits 2 Branches 0 Tags
06d32bf0c18848bc6e7c0335e184e295d58bbe9d
Commit Graph
122 Commits
Author SHA1 Message Date
trungkienbkhnandGitHub 06d32bf0c1 Bump version to 1.0.0 (#696) 2024-02-22 09:49:01 +01:00
PurfviewandGitHub 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
trungkienbkhnandGitHub 092067208b Add clip_timestamps and hallucination_silence_threshold options (#646) 2024-02-20 17:34:54 +01:00
PurfviewandGitHub 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
PurfviewandGitHub 00efce1696 Bugfix: Illogical "Avoid computing higher temperatures on no_speech" (#652) 2024-01-24 11:54:43 +01:00
metameandGitHub ad3c83045b support distil-whisper (#557) 2024-01-24 10:17:12 +01:00
PurfviewandGitHub 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
trungkienbkhnandGitHub 19329a3611 Word timing tweaks (#616) 2023-12-13 12:38:44 +01:00
Clayton YochumandGitHub 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
Dang Chuan Nguyen e1a218fab1 Bump version to 0.10.0 2023-11-24 23:19:47 +01:00
OscaarjsGitHuboscaarjs
 		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
Guillaume Klein 5a0541ea7d Bump version to 0.9.0 2023-09-18 16:21:37 +02:00
Guillaume KleinandGitHub e94711bb5c Add property WhisperModel.supported_languages (#476) 
* Expose function supported_languages

* Make it a method
 2023-09-14 17:42:02 +02:00
Guillaume KleinandGitHub 0048844f54 Expose function available_models (#475) 
* Expose function available_models

* Add test case
 2023-09-14 17:17:01 +02:00
Guillaume Klein a49097e655 Add some missing typing annotations in transcribe.py 2023-09-12 15:45:54 +02:00
Guillaume KleinandGitHub 81086f6d33 Always run the encoder at the beginning of the loop (#468) 2023-09-12 14:44:37 +02:00
Guillaume KleinandGitHub 727ab81f31 Improve error message for invalid task and language parameters (#466) 2023-09-12 10:02:23 +02:00
Guillaume Klein ad388cd394 Bump version to 0.8.0 2023-09-04 11:56:48 +02:00
Guillaume KleinandGitHub 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
Guillaume KleinandGitHub 1e6eb967c9 Add "large" alias for "large-v2" model (#453) 2023-09-04 11:54:42 +02:00
Guillaume KleinandGitHub f0ff12965a Expose generation parameter no_repeat_ngram_size (#449) 2023-09-01 17:31:30 +02:00
Guillaume KleinandGitHub 5871858a5f Force the garbage collector to run after decoding the audio with PyAV (#448) 2023-09-01 15:25:13 +02:00
MinorJinxandGitHub 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
Aisu WataGitHubAisu Wata
 		1562b02345 added repetition_penalty to TranscriptionOptions (#403) 
Co-authored-by: Aisu Wata <aisu.wata0@gmail.com>
 2023-08-06 10:08:24 +02:00
PurfviewandGitHub 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
PurfviewandGitHub 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
KHandGitHub 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
Guillaume Klein 5c17de1771 Bump version to 0.7.1 2023-07-24 11:10:12 +02:00
Guillaume KleinandGitHub 0f55c436fe Invalidate the cached encoder output when no_speech threshold is met (#376) 2023-07-24 10:57:15 +02:00
KHandGitHub 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
KHandGitHub 687db319e0 Remove duplicate code (#359) 2023-07-18 16:03:01 +02:00
Guillaume Klein 171d90dd1f Bump version to 0.7.0 2023-07-18 15:23:47 +02:00
Guillaume KleinandGitHub 0e051a5b77 Prepend prefix tokens with the initial timestamp token (#358) 2023-07-18 15:22:39 +02:00
HoonandGitHub 3b4a6aa1c2 Improve timestamp heuristics (#336) 
* Improve timestamp heuristics

* Chore
 2023-07-05 15:16:53 +02:00
zh-plusGitHubGuillaume Klein
 		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
Guillaume KleinandGitHub c0d93d0829 Avoid computing higher temperatures on no_speech segments (#225) 
Port commit https://github.com/openai/whisper/commit/e334ff141d5444fbf6904edaaf408e5b0b416fe8
 2023-07-03 10:20:36 +02:00
Guillaume KleinandGitHub 19c294f978 Squash long words at window and sentence boundaries (#226) 
Port commit https://github.com/openai/whisper/commit/255887f219e6b632bc1a6aac1caf28eecfca1bac
 2023-07-03 10:20:20 +02:00
FlippFuzzandGitHub fee52c9229 Allow users to input an Iterable of token ids into initial_prompt (#306) 
* Allow users to input an Iterable of token ids into initial_prompt

* Need to check for String first because string is also an Iterable
 2023-06-21 14:46:20 +02:00
Guillaume KleinandGitHub efc4f61d85 Do not specify the vocabulary file extension in the download pattern (#311) 2023-06-20 10:53:11 +02:00
khandGitHub ad58ba26ab Fix typo (#304) 
https://github.com/snakers4/silero-vad/discussions/319#discussion-5081706
 2023-06-16 07:37:45 +02:00
Guillaume Klein 2a00621564 Bump version to 0.6.0 2023-05-24 16:15:01 +02:00
Guillaume KleinandGitHub cf7c021573 Export __version__ at the module level (#258) 2023-05-24 15:50:37 +02:00
Guillaume KleinandGitHub 4db549b800 Make get_speech_timestamps backward compatible with the previous usage (#259) 2023-05-24 15:49:36 +02:00
Guillaume KleinandGitHub 723cb97483 Fix occasional IndexError on empty segments (#227) 2023-05-24 12:55:04 +02:00
Guillaume KleinandGitHub 6a2da9a95c Also catch client-side network exceptions when synchronizing models (#228) 2023-05-11 15:07:15 +02:00
Guillaume Klein 2d7c984bfc Reformat function download_model for clarity 2023-05-11 14:47:22 +02:00
David AxelrodGitHubGuillaume Klein
 		53d247b0bb retry model download locally if huggingface throws an http error. (#215) 
* rety model download locally if huggingface throws an http error.

* appease the linter

* key error fix

* use non internal lib error

Co-authored-by: Guillaume Klein <guillaumekln@users.noreply.github.com>

---------

Co-authored-by: Guillaume Klein <guillaumekln@users.noreply.github.com>
 2023-05-09 17:20:22 +02:00
Ozan CaglayanandGitHub 91f948b0d6 transcribe: return all language probabilities if requested (#210) 
* transcribe: return all language probabilities if requested

If return_all_language_probs is True, TranscriptionInfo structure
will have a list of tuples reflecting all language probabilities
as returned by the model.

* transcribe: fix docstring

* transcribe: remove return_all_lang_probs parameter
 2023-05-09 14:53:47 +02:00
FlippFuzzGitHubGuillaume Klein
 		5d8f3e2d90 Implement VadOptions (#198) 
* Implement VadOptions

* Fix line too long

./faster_whisper/transcribe.py:226:101: E501 line too long (111 > 100 characters)

* Reformatted files with black

* black .\faster_whisper\vad.py    
* black .\faster_whisper\transcribe.py

* Fix import order with isort

* isort .\faster_whisper\vad.py
* isort .\faster_whisper\transcribe.py

* Made recommended changes

Recommended in https://github.com/guillaumekln/faster-whisper/pull/198

* Fix typing of vad_options argument

---------

Co-authored-by: Guillaume Klein <guillaumekln@users.noreply.github.com>
 2023-05-09 12:47:02 +02:00
Guillaume Klein 89a4c7f1f0 Update docstring to clarify download_root and output_dir 2023-04-26 17:37:51 +02:00