sp-nitech/DNN-HSMM

pytorch implementation of DNN-HSMM for TTS

43
/ 100
Emerging

This project helps researchers in speech technology develop and evaluate new text-to-speech (TTS) systems. It takes linguistic and acoustic features from speech data as input and produces a trained model and generated acoustic features as output. The primary user is a speech synthesis researcher or engineer.

No commits in the last 6 months.

Use this if you are a speech synthesis researcher interested in experimenting with DNN-HSMM models for building statistical parametric text-to-speech systems.

Not ideal if you are looking for an out-of-the-box text-to-speech system for end-user applications or if you want to synthesize audio directly from text without needing to work with acoustic features.

speech-synthesis text-to-speech acoustic-modeling signal-processing voice-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

70

Forks

15

Language

Python

License

BSD-3-Clause

Last pushed

Mar 14, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/sp-nitech/DNN-HSMM"

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