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

Update CTranslate2 to 3.6.0

Browse Source
This commit is contained in:
Guillaume Klein
2023-02-16 17:01:19 +01:00
parent 0b53549902
commit cda834c8ea
2 changed files with 1 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -49,8 +49,6 @@ pip install -e .
GPU execution requires the NVIDIA libraries cuBLAS 11.x and cuDNN 8.x to be installed on the system. Please refer to the [CTranslate2 documentation](https://opennmt.net/CTranslate2/installation.html). GPU execution requires the NVIDIA libraries cuBLAS 11.x and cuDNN 8.x to be installed on the system. Please refer to the [CTranslate2 documentation](https://opennmt.net/CTranslate2/installation.html).
**Note for Windows users:** the published Windows wheels are currently not built with cuDNN, which is required to run the Whisper model on GPU. Consequently GPU execution is currently not possible on Windows out of the box. If you feel adventurous, a possible workaround is to [compile from sources](https://opennmt.net/CTranslate2/installation.html#install-from-sources).
## Usage ## Usage
### Model conversion ### Model conversion

2
requirements.txt
View File

@@ -1,3 +1,3 @@
av==10.* av==10.*
ctranslate2>=3.5.1,<4 ctranslate2>=3.6,<4
tokenizers==0.13.* tokenizers==0.13.*