b95420325b
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.
23 lines
248 B
Plaintext
23 lines
248 B
Plaintext
accelerate
|
|
cmudict
|
|
cn2an
|
|
g2p_en
|
|
gradio>=4.32
|
|
jieba
|
|
librosa==0.9.2
|
|
loguru
|
|
num2words
|
|
numpy<2
|
|
onnxruntime
|
|
onnxruntime-gpu
|
|
pyannote.audio>=3.1.0
|
|
pyloudnorm
|
|
pyopenjtalk-dict
|
|
pypinyin
|
|
pyworld-prebuilt
|
|
torch
|
|
torchaudio
|
|
torchvision
|
|
transformers
|
|
umap-learn
|