|
Download README.md from TheDailyOWO/splitwave-models: direct link, hf CLI and curl.
- Browser
- Download file 2.11 kB
-
https://huggingface.co/TheDailyOWO/splitwave-models/resolve/main/README.md
- Command line
-
hf download hf://TheDailyOWO/splitwave-models/README.md
-
curl -L -o README.md https://huggingface.co/TheDailyOWO/splitwave-models/resolve/main/README.md
2.11 kB
| license: other | |
| license_name: per-model | |
| tags: | |
| - audio-source-separation | |
| - music-source-separation | |
| - onnx | |
| - webgpu | |
| pipeline_tag: audio-to-audio | |
| # Splitwave models | |
| Browser-ready ONNX versions of the stem separation models used by | |
| [Splitwave](https://github.com/PolysheepCodes/Splitwave), a web app that splits songs into vocals, | |
| instrumental, lead and backing vocals on the visitor's own computer (WebGPU / WebAssembly). | |
| | File | Model | Does | Precision | | |
| |---|---|---|---| | |
| | `bs_roformer_fp16.onnx` | BS-RoFormer (ep 317, SDR 12.98) by viperx | vocals / instrumental (Best) | fp16 | | |
| | `mel_roformer_karaoke_fp16.onnx` | Mel-Band RoFormer karaoke (SDR 10.20) by aufr33 & viperx | lead / backing vocals (Best) | fp16 | | |
| | `mdx_voc_ft.onnx` | UVR-MDX-NET Voc_FT by the UVR team | vocals / instrumental (Fast) | fp32, unchanged | | |
| | `mdx_kara_2.onnx` | UVR_MDXNET_KARA_2 by the UVR team | lead / backing vocals (Fast) | fp32, unchanged | | |
| `manifest.json` lists each file's size and SHA-256. Splitwave checks downloads against it. | |
| ## Conversion | |
| The RoFormer networks were exported from the original PyTorch checkpoints with Splitwave's | |
| [`convert/roformer.py`](https://github.com/PolysheepCodes/Splitwave/blob/main/convert/roformer.py). They take | |
| one 8-second chunk's stereo STFT (`[1, 2050, 801, 2]`, n_fft 2048, hop 441) and return the complex mask to | |
| multiply it with. The STFT and inverse STFT happen in the app. The band split was restructured for WebGPU's | |
| limits, without changing the math. Each export was checked against the original model on real audio | |
| before the fp16 conversion (normalisation layers and rotary position tables kept in fp32). | |
| ## Credits and licenses | |
| The weights belong to their authors: the Ultimate Vocal Remover team (MDX-Net models), viperx | |
| (BS-RoFormer), and aufr33 & viperx (Mel-Band RoFormer karaoke). They were obtained through | |
| [python-audio-separator](https://github.com/nomadkaraoke/python-audio-separator)'s model repository. | |
| This repo redistributes them, converted for in-browser use, under the original authors' terms. Check those | |
| terms before reusing them. | |