Skip to main content

torchspleeter

Torchspleeter is a simplified interface for spleeter running completely on Torch, enabling cross platform functionality. It comes with a converted version of the 2stems model built in, and largely builds off the work of Tuan Nguyen.


Installation

pip install torchspleeter

or download from this repository and

pip install .


Usage

Torchspleeter comes with both a Python API and a standard CLI for simplistic use. Once installed, you can use torchspleeter -h for instructions on how to use the CLI.

For the Python API, an example is pretty simple:

from torchspleeter.command_interface import *

outputfiles=split_to_parts(input_audio_file,output_directory)

This will return two files, the first one isolates the vocals and the second everything but the vocals, using the default 2stems model included with torchspleeter. The number of files scales to the number of models specified.

This makes torchspleeter ideal for situations specifically where you need to isolate vocals, such as generating voice datasets.

See the testing example for in depth useage.


Reference


Contributing

If you'd like to contribute, please do! Please check the CONTRIBUTING.md for details on the best way to get started.


License

MIT.

Metadata

Release files for torchspleeter 0.1.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for torchspleeter 0.1.5
File Size Uploaded Provenance Actions
torchspleeter-0.1.5.tar.gz 88.8 MB Without provenance Details for torchspleeter-0.1.5.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for torchspleeter 0.1.5
File Interpreter ABI Platform Actions
torchspleeter-0.1.5-py3-none-any.whl Python 3 none any Details for torchspleeter-0.1.5-py3-none-any.whl

Total release size: 177.3 MB

Release files / torchspleeter-0.1.5.tar.gz

Download URL torchspleeter-0.1.5.tar.gz
Size 88.8 MB
Tags Source
SHA-256 checksum
How to use checksums
37fadbe95b4673ddaff29a016ca5af20fa5eedc670e805c5bafbc10fa923abbc
BLAKE2b-256 checksum
How to use checksums
8b17f56603c8f2360c9dc5255681e322e79955457cf0cd800177e0059f86f703
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.9.16

Release files / torchspleeter-0.1.5-py3-none-any.whl

Download URL torchspleeter-0.1.5-py3-none-any.whl
Size 88.6 MB
Tags Python 3
SHA-256 checksum
How to use checksums
922505f347b5356829411dd4bcd94cd066906c0b86293feccbb776a91bb3ec03
BLAKE2b-256 checksum
How to use checksums
ce4b9b50aedef4c4ddf0f55ba02b18d1aac15cc25f5ffe22d7e8333808b9ce5f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.9.16

Security for torchspleeter 0.1.5

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.5 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page