diff options
| author | yum <yum.food.vr@gmail.com> | 2024-06-05 18:15:47 -0700 |
|---|---|---|
| committer | yum <yum.food.vr@gmail.com> | 2024-06-05 18:15:47 -0700 |
| commit | 4f0fb5b17de990517e3c1de7ffee5d0f3c9a8961 (patch) | |
| tree | 2a1d1b33af881a651037af040b4ba8e7860a58db /Scripts/requirements_frozen.txt | |
| parent | 5638d86c97041de31217e058e411034143e9c882 (diff) | |
Upgrade faster-whisper with flash-attention2
This should be significantly more efficient than prior versions.
* add large-v3 & distilled variant
* simplify model acquisition code now that distilled models are part of
faster-whisper.
Diffstat (limited to 'Scripts/requirements_frozen.txt')
| -rw-r--r-- | Scripts/requirements_frozen.txt | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/Scripts/requirements_frozen.txt b/Scripts/requirements_frozen.txt index dd56b9d..1913457 100644 --- a/Scripts/requirements_frozen.txt +++ b/Scripts/requirements_frozen.txt @@ -1,11 +1,11 @@ -av==10.0.0 +av==12.0.0 certifi==2023.7.22 charset-normalizer==3.2.0 colorama==0.4.6 coloredlogs==15.0.1 -ctranslate2==3.19.0 +ctranslate2==4.2.1 editdistance==0.6.2 -faster-whisper @ https://github.com/guillaumekln/faster-whisper/archive/78d57d73c5b4a76b32d1d5a415e4e7aea760295c.tar.gz#sha256=824b441278d59fb7daff99f98823d492762e279980922308a2e0833ac8e49c5c +faster-whisper @ https://github.com/guillaumekln/faster-whisper/archive/2f6913efc85306fc4f900da6c67f9a06a7d54a3d.tar.gz#sha256=c389ad787c8cdafcb13d31f8bae788083eb4e490819aad6b49d76c82e490a388 filelock==3.12.3 flatbuffers==23.5.26 fsspec==2023.9.0 |