sp-nitech/diffsptk

A differentiable version of SPTK

59
/ 100
Established

This project offers essential speech signal processing tools, like those for analyzing pitch, converting text to speech, and handling audio, but with a unique twist: they're designed to integrate directly into machine learning models. It takes raw audio waveforms or speech features as input and outputs processed speech features or reconstructed audio. This is for researchers and developers building advanced speech AI systems.

196 stars. Available on PyPI.

Use this if you are developing neural network models for speech applications and need to incorporate traditional speech processing algorithms in a way that allows for end-to-end optimization.

Not ideal if you are a practitioner looking for a standalone application for basic audio editing or standard speech analysis without integrating into a deep learning pipeline.

speech-recognition speech-synthesis audio-analysis voice-processing machine-learning-research
Maintenance 10 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 14 / 25

How are scores calculated?

Stars

196

Forks

20

Language

Python

License

Apache-2.0

Last pushed

Feb 26, 2026

Commits (30d)

0

Dependencies

11

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sp-nitech/diffsptk"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.