search

facebookresearch / denoiser

Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities.
Other
1.65k stars 302 forks source link

CUDA out of memory when set --device="cuda" #87

Closed lethanhson9901 closed 3 years ago

lethanhson9901 commented 3 years ago

Hi, I'm using your pre-trained model to enhance audio with GPU. In particular, I run: !python3 -m denoiser.enhance --noisy_dir=noisy/700to1300/ --out_dir=cleaned/noisy --device="cuda" --sample_rate 22050

I set --device="cuda" but I got this error:

INFO:denoiser.pretrained:Loading pre-trained real time H=48 model trained on DNS. Traceback (most recent call last): File "/usr/lib/python3.7/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/usr/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/content/drive/My Drive/denoiser/denoiser/enhance.py", line 156, in enhance(args, local_out_dir=args.out_dir) File "/content/drive/My Drive/denoiser/denoiser/enhance.py", line 143, in enhance estimate = get_estimate(model, noisy_signals, args) File "/content/drive/My Drive/denoiser/denoiser/enhance.py", line 68, in get_estimate estimate = model(noisy) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(*input, kwargs) File "/content/drive/My Drive/denoiser/denoiser/demucs.py", line 176, in forward x = encode(x) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(*input, *kwargs) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/container.py", line 139, in forward input = module(input) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(input, kwargs) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/conv.py", line 298, in forward return self._conv_forward(input, self.weight, self.bias) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/conv.py", line 295, in _conv_forward self.padding, self.dilation, self.groups) RuntimeError: CUDA out of memory. Tried to allocate 4.11 GiB (GPU 0; 15.90 GiB total capacity; 12.99 GiB already allocated; 2.00 GiB free; 13.00 GiB reserved in total by PyTorch)

I run on google-colab pro, but I don't run any other session. I don't know why. I also set batch size to 1, num_workers=1. Pls, help me! Thanks!

adefossez commented 3 years ago

Try to add --streaming, you are likely trying to separate very large audio files.

lethanhson9901 commented 3 years ago

It's work, many thanks!