JusperLee/Dual-Path-RNN-Pytorch
Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation implemented by Pytorch
This project helps separate individual voices from a single audio recording where multiple people are speaking at once. You feed in an audio file with mixed speech, and it produces separate audio files, each containing the isolated speech of one person. This is useful for researchers and developers working on speech processing applications, such as improving transcription accuracy or enhancing specific voices.
464 stars. No commits in the last 6 months.
Use this if you need to cleanly isolate individual speech signals from a single audio track containing a mixture of voices.
Not ideal if you're looking for a ready-to-use application with a graphical interface for end-users, as this requires technical setup and command-line execution.
Stars
464
Forks
69
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 14, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JusperLee/Dual-Path-RNN-Pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pytorch/audio
Data manipulation and transformation for audio signal processing, powered by PyTorch
asteroid-team/asteroid
The PyTorch-based audio source separation toolkit for researchers
deezer/spleeter
Deezer source separation library including pretrained models.
audeering/opensmile
The Munich Open-Source Large-Scale Multimedia Feature Extractor
audeering/opensmile-python
Python package for openSMILE