andi611/ZeroSpeech-TTS-without-T

A Pytorch implementation for the ZeroSpeech 2019 challenge.

38
/ 100
Emerging

This project helps researchers and developers explore speech synthesis without relying on traditional text inputs. It takes raw speech audio and processes it to extract fundamental sound units, then reconstructs new speech. This is useful for scientists working on speech technology who want to create synthesized voices directly from audio examples, bypassing the need for written text.

112 stars. No commits in the last 6 months.

Use this if you are a speech technology researcher looking to experiment with unsupervised voice conversion or speech synthesis that doesn't require transcribed text.

Not ideal if you need a ready-to-use text-to-speech system for practical applications or if you are not comfortable with machine learning research setups.

speech-synthesis voice-conversion unsupervised-learning audio-research linguistic-units
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

112

Forks

12

Language

Python

License

MIT

Last pushed

Nov 12, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/andi611/ZeroSpeech-TTS-without-T"

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