openai/whisper issues and pull requests

#2343 - Add option to carry initial_prompt with the sliding window

Pull Request - State: open - Opened by kittsil 13 days ago - 4 comments

#2332 - pinning numpy<2 in tests

Pull Request - State: closed - Opened by jongwook 21 days ago

#2329 - Transcribe on GPU

Pull Request - State: open - Opened by take0x 22 days ago - 5 comments

#2309 - Create CHIPBoT IDfy

Pull Request - State: closed - Opened by edoerpani about 1 month ago

#2307 - Relax triton requirements for compatibility with pytorch 2.4 and newer

Pull Request - State: closed - Opened by xingjianan about 1 month ago - 1 comment

#2306 - word_stream_callback To get the ready words.

Pull Request - State: open - Opened by erfantarighi about 1 month ago - 1 comment

#2301 - Fix/torch load weights only warning

Pull Request - State: open - Opened by Ultr4Dev about 2 months ago - 2 comments

#2298 - Pin numpy to 1.26.4

Pull Request - State: open - Opened by agardnerIT about 2 months ago - 3 comments

#2287 - Update Documentation for Audio Processing Functions

Pull Request - State: open - Opened by salimshakeel 2 months ago

#2286 - Improved Documentation

Pull Request - State: closed - Opened by salimshakeel 2 months ago

#2281 - Main

Pull Request - State: open - Opened by ashishpatel26 2 months ago

#2265 - Support for Buffered Audio Data

Pull Request - State: open - Opened by kentslaney 3 months ago - 2 comments

#2256 - Support longer audio files reducing memory usage with chunking

Pull Request - State: open - Opened by ggarber 3 months ago - 1 comment

#2240 - Enhancements

Pull Request - State: closed - Opened by sanowl 3 months ago - 1 comment

#2229 - Update CHANGELOG.md

Pull Request - State: closed - Opened by junwenyin 4 months ago - 1 comment

#2222 - docs: include ffmpeg installations instructions for Docker

Pull Request - State: open - Opened by rishi-raj-jain 4 months ago

#2207 - Update README.md

Pull Request - State: open - Opened by littinrajan 4 months ago

#2206 - Update README.md

Pull Request - State: closed - Opened by littinrajan 4 months ago

#2201 - Fix: typo in dataset reference text

Pull Request - State: open - Opened by CharlesCNorton 4 months ago

#2200 - Fix: typo in dataset preparation documentation

Pull Request - State: open - Opened by CharlesCNorton 4 months ago

#2197 - Fix beam search with batch processing in Whisper decoding

Pull Request - State: open - Opened by zuazo 4 months ago

#2193 - Create python-app.yml

Pull Request - State: open - Opened by satanistninja666 4 months ago

#2189 - Add probability for each token

Pull Request - State: open - Opened by khalilfiremind 4 months ago - 1 comment

#2187 - feat: add comments created by Github Copilot

Pull Request - State: closed - Opened by zzy981019 4 months ago

#2185 - Feat/add token confidence

Pull Request - State: closed - Opened by nathanael-perraudin-synth 4 months ago

#2166 - Normalizer mod

Pull Request - State: closed - Opened by ethangearey 5 months ago

#2161 - Add error handling to log_mel_spectrogram function

Pull Request - State: open - Opened by MadhumithaKolkar 5 months ago

#2153 - Dependabot configuration to update actions in workflows

Pull Request - State: closed - Opened by ScottBrenner 5 months ago - 1 comment

#2152 - test

Pull Request - State: closed - Opened by lundgren-greg 5 months ago - 1 comment

#2130 - Add `enable_generator` in `transcribe()`

Pull Request - State: closed - Opened by jhj0517 6 months ago

#2112 - Omit space prefix in initial_prompt for spaceless languages.

Pull Request - State: open - Opened by ryanheise 6 months ago

#2111 - whisper/transcribe: fix typo on supersedes

Pull Request - State: open - Opened by RuffaloLavoisier 6 months ago

#2097 - Hiding the ffmpeg popup that appears momentarily

Pull Request - State: open - Opened by Menonro 6 months ago - 3 comments

#2092 - Update setup.py

Pull Request - State: open - Opened by tejhande 7 months ago - 1 comment

#2070 - add hotwords feature

Pull Request - State: open - Opened by jax-explorer 7 months ago - 7 comments

#2066 - Update to requirements.txt

Pull Request - State: open - Opened by DeeprSoni 7 months ago

#2066 - Update to requirements.txt

Pull Request - State: open - Opened by DeeprSoni 7 months ago

#2066 - Update to requirements.txt

Pull Request - State: open - Opened by DeeprSoni 7 months ago

#2049 - Updating README and doc strings to reflect that n_mels can now be 128

Pull Request - State: open - Opened by lvaughn 7 months ago

#2043 - Fix window end heuristic for hallucination_silence_threshold

Pull Request - State: open - Opened by ryanheise 7 months ago

#2041 - Create Security Policy

Pull Request - State: open - Opened by diogoteles08 7 months ago

#2031 - Documentation update of utils.py

Pull Request - State: open - Opened by louisbrulenaudet 7 months ago

#2005 - Prevent infinite loop for out-of-bound timestamps in clip_timestamps

Pull Request - State: open - Opened by jbaudanza 8 months ago - 1 comment

#2004 - Add language_bias parameter to detect_language

Pull Request - State: open - Opened by jbaudanza 8 months ago - 2 comments

#1980 - Enhancement: allow processing already-in-memory audio file content

Pull Request - State: open - Opened by nleve 8 months ago

#1980 - Enhancement: allow processing already-in-memory audio file content

Pull Request - State: open - Opened by nleve 8 months ago

#1979 - Fix model.transcribe

Pull Request - State: closed - Opened by jbetker 8 months ago - 1 comment

#1959 - add repeat audio back

Pull Request - State: open - Opened by yuekaizhang 9 months ago

#1947 - Do not assert for a negative timestamp

Pull Request - State: open - Opened by gaspardpetit 9 months ago

#1946 - Create a search based document for whisper

Pull Request - State: closed - Opened by James4Ever0 9 months ago - 1 comment

#1944 - fix error on windows machines in timing.py

Pull Request - State: open - Opened by pkp24 9 months ago

#1926 - There are 100 languages instead of 99.

Pull Request - State: closed - Opened by MarkChrisE2091 9 months ago - 2 comments

#1925 - Added Unicode not supported Msg for environments that don't support it

Pull Request - State: open - Opened by alaamroue 9 months ago

#1920 - Reduce memory usage in load_audio

Pull Request - State: open - Opened by ryanheise 9 months ago

#1912 - Enhancement: Accept Path type for `audio_path` parameter and return `output_path`

Pull Request - State: open - Opened by 169 10 months ago

#1903 - Bugfix: Illogical "Avoid computing higher temperatures on no_speech"

Pull Request - State: open - Opened by Purfview 10 months ago - 7 comments

#1898 - feat(whisper): more intelegent token insertion of special words.

Pull Request - State: closed - Opened by PascalHauriUnique 10 months ago

#1887 - Fix triton env marker

Pull Request - State: closed - Opened by 169 10 months ago - 7 comments

#1866 - detect if Mac's Metal Performance Shaders are available

Pull Request - State: closed - Opened by rgbkrk 10 months ago - 1 comment

#1857 - Replace regular expressions

Pull Request - State: open - Opened by eukub 10 months ago - 2 comments

#1838 - Skip silence around hallucinations

Pull Request - State: closed - Opened by ryanheise 10 months ago - 25 comments

#1831 - (slightly) More robust conversion

Pull Request - State: open - Opened by svaningelgem 10 months ago

#1829 - Change version for python

Pull Request - State: open - Opened by AshishKumarGrover 10 months ago

#1810 - Making a small type change

Pull Request - State: open - Opened by OliverCai0 11 months ago

#1802 - Relax triton requirements for compatibility with pytorch 2.1 and newer

Pull Request - State: closed - Opened by eindenbom 11 months ago - 1 comment

#1787 - Added number content_frames and dtype to transcribe results

Pull Request - State: open - Opened by ZuluPro 11 months ago - 3 comments

#1786 - Add subtitle format and font color in word_options dict

Pull Request - State: open - Opened by MatteoFasulo 11 months ago

#1777 - Update actions/checkout to v4

Pull Request - State: open - Opened by salehhashemi1992 11 months ago

#1764 - Improve --model argument handling and help message

Pull Request - State: open - Opened by spartanhaden 11 months ago - 5 comments

#1763 - Update description of n_mels according to changes mel_filters function

Pull Request - State: open - Opened by kamushekp 11 months ago

#1761 - large-v3

Pull Request - State: closed - Opened by jongwook 11 months ago - 1 comment

#1759 - remove tiktoken pin

Pull Request - State: closed - Opened by jongwook 11 months ago

#1751 - docs: Disambiguation of the term "relative speed" in the README

Pull Request - State: closed - Opened by philippefutureboy 11 months ago

#1741 - doc(README): remove typo

Pull Request - State: closed - Opened by AranavMahalpure 11 months ago - 1 comment

#1729 - Add new option to generate subtitles by a specific number of words

Pull Request - State: closed - Opened by amolinasalazar 11 months ago - 7 comments

#1704 - Add subtitle_format option to word_options dict

Pull Request - State: closed - Opened by MatteoFasulo 12 months ago - 2 comments

#1682 - handling transcribe exceptions.

Pull Request - State: closed - Opened by zuccon about 1 year ago

#1661 - Python

Pull Request - State: closed - Opened by SP0919 about 1 year ago

#1643 - Update model-card.md

Pull Request - State: closed - Opened by NinoRisteski about 1 year ago

#1642 - Add Hatch : modern, extensible python project management

Pull Request - State: closed - Opened by chaukematimu about 1 year ago

#1605 - added support for bfloat16 datatype to be used for Intel Xeon processors

Pull Request - State: open - Opened by devpramod-intel about 1 year ago - 3 comments

#1596 - fix-space-issue

Pull Request - State: closed - Opened by jhj0517 about 1 year ago - 2 comments

#1580 - Detect lang

Pull Request - State: closed - Opened by GitKraug about 1 year ago

#1571 - refactor: PyTorchInference initialization

Pull Request - State: closed - Opened by arjun-234 about 1 year ago - 5 comments

#1568 - Patch 3

Pull Request - State: closed - Opened by GrayHatAlex about 1 year ago

#1559 - word timing tweaks

Pull Request - State: closed - Opened by taylorchu about 1 year ago - 5 comments

#1528 - Add .pre-commit-config.yaml

Pull Request - State: closed - Opened by kimdwkimdw about 1 year ago

#1526 - fix doc of TextDecoder

Pull Request - State: closed - Opened by HSQ79815 about 1 year ago

#1511 - Use thread-safe loading of mel matrix IN audio.py

Pull Request - State: closed - Opened by mzamini92 about 1 year ago - 5 comments

#1501 - added parser argument to support MPS by default

Pull Request - State: open - Opened by NripeshN about 1 year ago - 1 comment

#1483 - Avoid rearranging all caches

Pull Request - State: closed - Opened by wangchou over 1 year ago

#1481 - Add GPU Support for Apple Silicon Macs

Pull Request - State: closed - Opened by NripeshN over 1 year ago - 2 comments

#1476 - fix bug with getting dictionary items in utils

Pull Request - State: open - Opened by bayesfactor over 1 year ago - 1 comment

#1473 - Add support for AMD GPU (ROCm Platform)

Pull Request - State: open - Opened by yaomingamd over 1 year ago - 9 comments

#1465 - Fix language detection func

Pull Request - State: closed - Opened by jan-grzybek-ampere over 1 year ago

#1461 - Improve timestamp heuristics.

Pull Request - State: closed - Opened by ryanheise over 1 year ago - 4 comments

#1460 - Add minor grammar touch-up

Pull Request - State: closed - Opened by serhatgktp over 1 year ago

#1431 - try1

Pull Request - State: closed - Opened by bonchardon over 1 year ago - 1 comment

#1402 - Create Etheria text

Pull Request - State: closed - Opened by PaigeLeila over 1 year ago

#1396 - Fix exception when generating the subtitles for an audio with no speech

Pull Request - State: closed - Opened by jordimas over 1 year ago - 1 comment

GitHub / openai/whisper issues and pull requests