keonlee9420/Parallel-Tacotron2

PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling

47
/ 100
Emerging

This project aims to convert written text into natural-sounding speech quickly and efficiently. You provide written sentences or paragraphs, and it generates audio files of a voice speaking that text. It's intended for developers or researchers working on building and improving speech synthesis systems, allowing them to experiment with advanced text-to-speech models.

191 stars. No commits in the last 6 months.

Use this if you are a developer or researcher focused on developing and refining non-autoregressive neural text-to-speech models, and you need a PyTorch implementation to experiment with.

Not ideal if you are an end-user simply looking for a ready-to-use application to convert text to speech without needing to develop or debug the underlying model.

speech-synthesis text-to-speech voice-generation neural-networks machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

191

Forks

44

Language

Python

License

MIT

Last pushed

Nov 18, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/keonlee9420/Parallel-Tacotron2"

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