soobinseo/Tacotron-pytorch

Pytorch implementation of Tacotron

47
/ 100
Emerging

This project helps machine learning engineers and researchers implement a text-to-speech model. It takes a collection of text scripts and corresponding audio files as input, processes them, and then trains a model that can convert new text into synthesized speech. The primary users are those working on speech synthesis research or building custom voice generation systems.

206 stars. No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher looking for a PyTorch implementation of the Tacotron text-to-speech model to train with your own datasets.

Not ideal if you need an out-of-the-box text-to-speech solution without programming or if you are looking for a highly optimized, production-ready system.

speech-synthesis text-to-speech voice-generation deep-learning audio-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

206

Forks

40

Language

Python

License

Apache-2.0

Last pushed

Nov 01, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/soobinseo/Tacotron-pytorch"

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