open-unmix-pytorch
open-unmix-pytorch copied to clipboard
Open-Unmix - Music Source Separation for PyTorch
## 🐛 Bug When running the Colab just for extracting the stems from the youtube video, we get `NameError: name 'predict' is not defined`. This might have been overlooked as...
I'm not sure if this is intentional or not but the `wiener_win_len` argument is not used by the `hub_loader` in the following [code](https://github.com/sigsep/open-unmix-pytorch/blob/master/openunmix/utils.py). ```python # otherwise we load the separator...
If I want to download the umx pretrained model, I can get the target.json and target.pth files from Zenodo, but it's lacking the separator.json: https://zenodo.org/record/3340804 It's pretty easy to generate...
Hello, I've been interested in running various oracle benchmark methods to check if different types of spectrogram (CQT, etc.) can be useful for source separation. Initially, I was working with...
Currently using `train.py --nb-channels 1` will apply a downmix in the spectral domain inside the model to feed in only single channel audio. However, I can think about applications where...
Hello, If you run this code: import torch eps = np.finfo(np.float).eps N = track.audio.shape[0] # remember number of samples for future use X = stft(track.audio.T, nperseg=4096, noverlap=3072)[-1] (I, F, T)...
Bumps [scikit-learn](https://github.com/scikit-learn/scikit-learn) from 0.22 to 1.5.0. Release notes Sourced from scikit-learn's releases. Scikit-learn 1.5.0 We're happy to announce the 1.5.0 release. You can read the release highlights under https://scikit-learn.org/stable/auto_examples/release_highlights/plot_release_highlights_1_5_0.html and...
Bumps [tqdm](https://github.com/tqdm/tqdm) from 4.62.2 to 4.66.3. Release notes Sourced from tqdm's releases. tqdm v4.66.3 stable cli: eval safety (fixes CVE-2024-34062, GHSA-g7vv-2v7x-gj9p) tqdm v4.66.2 stable pandas: add DataFrame.progress_map (#1549) notebook: fix...