stem-splitter
BS-RoFormerを使用して音声を6ステム（bass、drums、other、vocals、guitar、piano）に分離するPythonパッケージです。
CUDA推論ではFP16 mixed precisionとTransformer層のtorch.compileを既定で使用します。compileを使用できない環境では警告を出してeager実行へフォールバックします。Windowsでcompileを使用する場合は、PyTorchのバージョンに対応するtriton-windowsを別途インストールしてください。
初回推論ではGPU向けカーネルを生成するため、数十秒程度のcompile待ちが発生します。生成後のカーネルはキャッシュされます。
pip install stem-splitter
stem-splitter input.wav --out-dir output
compileを明示的に無効化する場合は--no-compile、CUDAでFP32推論を行う場合は--full-precisionを指定します。
1 maintainer
Metadata
1 maintainer
Release files for stem-splitter 0.0.7
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| stem_splitter-0.0.7.tar.gz | 18.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| stem_splitter-0.0.7-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 36.2 kB
Release files / stem_splitter-0.0.7.tar.gz
| Download URL | stem_splitter-0.0.7.tar.gz |
|---|---|
| Size | 18.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d2737f1b89d198f3997f2796751e9ab7ff63549ee453cde6b4d05e52ca3852a7
|
|
BLAKE2b-256 checksum How to use checksums |
e603df7534106902d75366718ecbf75bc45873e0ec25355d9a80c64b19d9f234
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.6
|
Release files / stem_splitter-0.0.7-py3-none-any.whl
| Download URL | stem_splitter-0.0.7-py3-none-any.whl |
|---|---|
| Size | 17.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
456a305af2766551442c42243e4edcda5c03acdb02db3bc042a8d2ccb337ca82
|
|
BLAKE2b-256 checksum How to use checksums |
e8c1a0bc53301ae4f41222881e7422a869e597981ebe53a23a46af08d60b037e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.6
|
