Improve: Changed PyTorch to an optional dependency when used style_bert_vits2 as a library
ONNXRuntime has relied on CUDA 12.x / cuDNN 9.x by default since v1.19.0, while PyTorch finally supports cuDNN 9 since v2.4.0. Therefore, unless the pinning of torch<2.4 is eliminated, CUDA cannot be used with the latest version of ONNXRuntime.
This commit is contained in:
@@ -11,6 +11,7 @@ loguru
|
||||
num2words
|
||||
numpy<2
|
||||
onnxruntime
|
||||
onnxruntime-gpu
|
||||
onnxsim
|
||||
protobuf==4.25
|
||||
psutil
|
||||
@@ -22,7 +23,7 @@ pypinyin
|
||||
pyworld-prebuilt
|
||||
stable_ts
|
||||
tensorboard
|
||||
torch<2.4
|
||||
torchaudio<2.4
|
||||
torch
|
||||
torchaudio
|
||||
transformers
|
||||
umap-learn
|
||||
|
||||
Reference in New Issue
Block a user