kaituoxu/Tacotron2

A PyTorch implementation of Tacotron2, an end-to-end text-to-speech(TTS) system described in "Natural TTS Synthesis By Conditioning Wavenet On Mel Spectrogram Predictions".

34
/ 100
Emerging

This tool helps researchers and voice synthesis engineers convert written text into natural-sounding speech. You provide text input, and it generates corresponding audio files. It is primarily used by those working on advanced speech synthesis projects and experimenting with state-of-the-art neural network architectures.

No commits in the last 6 months.

Use this if you need to generate high-quality, human-like speech from text and are comfortable working with a command-line interface and training deep learning models.

Not ideal if you're looking for a simple, off-the-shelf text-to-speech application without any deep learning model training or customization.

speech-synthesis voice-generation natural-language-processing audio-engineering
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

52

Forks

14

Language

Python

License

Last pushed

Jan 30, 2019

Commits (30d)

0

Get this data via API

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

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