Yangyangii/AdvDCTTS

Implementation of DCTTS with Adversarial Training

27
/ 100
Experimental

This project helps speech synthesis researchers create realistic, high-quality synthetic speech directly from text. You input a written script and a pre-processed speech dataset, and it produces audio files of the text being spoken. It's designed for researchers and engineers working on text-to-speech (TTS) systems who want to experiment with advanced deep learning models.

No commits in the last 6 months.

Use this if you are a speech synthesis researcher looking to train a text-to-speech model using adversarial training techniques to generate sharp, clear spectrograms and natural-sounding speech.

Not ideal if you are a content creator or end-user simply looking to convert text to speech without deep involvement in model training and experimentation.

speech-synthesis text-to-speech voice-generation audio-engineering deep-learning-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

12

Forks

3

Language

Python

License

Last pushed

Dec 30, 2019

Commits (30d)

0

Get this data via API

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

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