nuwave2
nuwave2 copied to clipboard
maum-ai
NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates @ INTERSPEECH 2022
Hello, I'm very interested in your great work! I have 3 questions, would you mind helping me with them? 1. I was wondering whether your network could be extended to...
I installed the git, created an venv, activated it, dl'd the dataset, removed the speakers, oriented the yaml and when I go to run the flac2wav conversions, I get the...
I have been using your open-source code to perform 16k to 48k speech reconstruction. I utilized the default 8-step inference process and tested it on the untrimmed test set using...
I've inserted view as real after setting the return_complex values to true because PyTorch 2.0 deprecates the return_complex into runtime errors. This allows for use on Mac with cpu. After...
2023-08-02 12:00:07.518068: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] **TF-TRT Warning: Could not find TensorRT /usr/local/lib/python3.10/dist-packages/torch/functional.py:641: UserWarning: stft with return_complex=False is deprecated**. In a future pytorch release, stft will return complex tensors for all inputs,...
the command i executed : python inference.py -c nuwave2_02_16_13_epoch=629.ckpt -i 5dk.mp3 --sr 16 here results  ``` D:\86 se courses youtube kanali\upsample audio>python inference.py -c nuwave2_02_16_13_epoch=629.ckpt -i 5dk.mp3 --sr 16...
When running `inference.py`, an error occurs: File "C:\Users\User\nuwave2\inference.py", line 71, in model = NuWave2(hparams).to(args.device) File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\lightning_fabric\utilities\device_dtype_mixin.py", line 54, in to return super().to(*args, **kwargs) File "C:\Users\User\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1145, in to return...
Hello. I want to improve audio of my recordings I didn't understand from readme that how can I achieve this shown in demo in demo you have Section Ⅱ: Examples...
Hello, I re-trained your model, 1.5M steps Their performance is a bit behind SOTA, but may be useful as a research work to compare and compare.
