keonlee9420/Robust_Fine_Grained_Prosody_Control

PyTorch Implementation of Robust and fine-grained prosody control of end-to-end speech synthesis

40
/ 100
Emerging

This project helps speech synthesis researchers and developers create natural-sounding spoken audio from text. It takes a text input and a reference speaker's voice, then generates a synthesized speech output that mimics the prosody (rhythm, stress, and intonation) of the reference speaker. It's designed for those working on advanced text-to-speech models.

No commits in the last 6 months.

Use this if you are a speech researcher or developer looking to experiment with fine-grained control over prosody in end-to-end speech synthesis using PyTorch.

Not ideal if you need an out-of-the-box text-to-speech system for production without deep technical involvement or if you don't have access to a powerful GPU.

speech-synthesis text-to-speech prosody-control voice-cloning audio-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

41

Forks

11

Language

Python

License

BSD-3-Clause

Last pushed

Feb 20, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/keonlee9420/Robust_Fine_Grained_Prosody_Control"

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