search

jik876 / hifi-gan

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
MIT License
1.92k stars 506 forks source link

Specific environment version #28

Closed peacefulxy closed 3 years ago

peacefulxy commented 3 years ago

When training I have a runtime error: : cuDNN error: CUDNN_STATUS_EXECUTION_FAILED. Could you please provide specific version of your environment, including python, cuda and cudnn? Thank you very much.

jik876 commented 3 years ago

Sorry for late reply. We used python3.7, pytorch1.6 and CUDA 10.1 most often in our experiments. It would be a good try to reinstall pytorch.

jik876 commented 3 years ago

I close this as there are no recent updates. Please reopen if you need additional comments.

chikiuso commented 2 years ago

Hi, I found the error "RuntimeError: CUDA error: no kernel image is available for execution on the device" with this setting, or anything I did wrong on the installation? thanks

chikiuso commented 2 years ago

The full error message is as below, may I seek your help how could I solve it? thanks :

checkpoints directory : cp_hifigan Epoch: 1 /root/hifi-gan/meldataset.py:15: WavFileWarning: Chunk (non-data) not understood, skipping it. sampling_rate, data = read(full_path) /root/hifi-gan/meldataset.py:15: WavFileWarning: Chunk (non-data) not understood, skipping it. sampling_rate, data = read(full_path) /root/hifi-gan/meldataset.py:15: WavFileWarning: Chunk (non-data) not understood, skipping it. sampling_rate, data = read(full_path) /root/hifi-gan/meldataset.py:15: WavFileWarning: Chunk (non-data) not understood, skipping it. sampling_rate, data = read(full_path) Traceback (most recent call last): File "train.py", line 271, in main() File "train.py", line 267, in main train(0, a, h) File "train.py", line 122, in train y_g_hat = generator(x) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/root/hifi-gan/models.py", line 101, in forward x = self.conv_pre(x) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 714, in _call_impl result = hook(self, input) File "/usr/local/lib/python3.7/dist-packages/torch/nn/utils/weight_norm.py", line 55, in call setattr(module, self.name, self.compute_weight(module)) File "/usr/local/lib/python3.7/dist-packages/torch/nn/utils/weight_norm.py", line 18, in compute_weight return _weight_norm(v, g, self.dim) RuntimeError: CUDA error: no kernel image is available for execution on the device