search

yeyupiaoling / Whisper-Finetune

Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment
Apache License 2.0
866 stars 143 forks source link

建議您整理一下 requirements.txt 及 readme.md #71

Closed bardenthenry closed 4 months ago

bardenthenry commented 6 months ago

若按照您教學的版本安裝環境，faster whisper 會無法使用，因為最新版的僅支援 cuda 12，但您的 readme 中的安裝環境還停留在 cuda 11

yeyupiaoling commented 6 months ago

只要你安装的pytorch支持cuda 12就可以的，这个跟我的requirements.txt没有关系，主要是看你安装了那个版本的pytorch。我目前也只是使用cuda11,8，一直没有问题