heimoshuiyu/whisper
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Release 20230307

Browse Source
This commit is contained in:
Jong Wook Kim
2023-03-07 20:36:29 -08:00
parent 919a713499
commit 26807ec6d3
2 changed files with 21 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
CHANGELOG.md
View File

@@ -1,25 +1,31 @@
# CHANGELOG # CHANGELOG
## [v20230307](https://github.com/openai/whisper/releases/tag/v202303067)
* Fix the repetition/hallucination issue identified in #1046 ([#1052](https://github.com/openai/whisper/pull/1052))
* Use triton==2.0.0 ([#1053](https://github.com/openai/whisper/pull/1053))
* Install triton in x86_64 linux only ([#1051](https://github.com/openai/whisper/pull/1051))
* update setup.py to specify python >= 3.8 requirement
## [v20230306](https://github.com/openai/whisper/releases/tag/v20230306) ## [v20230306](https://github.com/openai/whisper/releases/tag/v20230306)
* #1021: remove auxiliary audio extension * remove auxiliary audio extension ([#1021](https://github.com/openai/whisper/pull/1021))
* #1038: apply formatting with `black`, `isort`, and `flake8` * apply formatting with `black`, `isort`, and `flake8` ([#1038](https://github.com/openai/whisper/pull/1038))
* #869: word-level timestamps in `transcribe()` * word-level timestamps in `transcribe()` ([#869](https://github.com/openai/whisper/pull/869))
* #1033: Decoding improvements * Decoding improvements ([#1033](https://github.com/openai/whisper/pull/1033))
* #894: Update README.md * Update README.md ([#894](https://github.com/openai/whisper/pull/894))
* #914: Fix infinite loop caused by incorrect timestamp tokens prediction * Fix infinite loop caused by incorrect timestamp tokens prediction ([#914](https://github.com/openai/whisper/pull/914))
* #889: drop python 3.7 support * drop python 3.7 support ([#889](https://github.com/openai/whisper/pull/889))
## [v20230124](https://github.com/openai/whisper/releases/tag/v20230124) ## [v20230124](https://github.com/openai/whisper/releases/tag/v20230124)
* #887: handle printing even if sys.stdout.buffer is not available * handle printing even if sys.stdout.buffer is not available ([#887](https://github.com/openai/whisper/pull/887))
* #228: Add TSV formatted output in transcript, using integer start/end time in milliseconds * Add TSV formatted output in transcript, using integer start/end time in milliseconds ([#228](https://github.com/openai/whisper/pull/228))
* #333: Added `--output_format` option * Added `--output_format` option ([#333](https://github.com/openai/whisper/pull/333))
* #864: Handle `XDG_CACHE_HOME` properly for `download_root` * Handle `XDG_CACHE_HOME` properly for `download_root` ([#864](https://github.com/openai/whisper/pull/864))
* #867: use stdout for printing transcription progress * use stdout for printing transcription progress ([#867](https://github.com/openai/whisper/pull/867))
* #659: Fix bug where mm is mistakenly replaced with hmm in e.g. 20mm * Fix bug where mm is mistakenly replaced with hmm in e.g. 20mm ([#659](https://github.com/openai/whisper/pull/659))
* #859: print '?' if a letter can't be encoded using the system default encoding * print '?' if a letter can't be encoded using the system default encoding ([#859](https://github.com/openai/whisper/pull/859))
## [v20230117](https://github.com/openai/whisper/releases/tag/v20230117) ## [v20230117](https://github.com/openai/whisper/releases/tag/v20230117)

2
whisper/version.py
View File

@@ -1 +1 @@
__version__ = "20230306" __version__ = "20230307"