diver-j/melgan-multi

MelGAN Multi GPU Implementation.

20
/ 100
Experimental

This project helps audio engineers and researchers generate realistic human speech from text using deep learning. It takes the LJSpeech dataset of audio recordings and their corresponding text, then processes them to train a model that can synthesize new speech. The primary users are individuals working on text-to-speech systems or speech synthesis research.

No commits in the last 6 months.

Use this if you need to train a high-quality speech synthesis model using generative adversarial networks, especially if you have access to multiple GPUs for faster training.

Not ideal if you're looking for a ready-to-use speech synthesis tool for immediate audio generation without training, or if you don't have access to NVIDIA GPUs and CUDA.

speech-synthesis text-to-speech audio-generation deep-learning-research voice-technology
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Python

License

Last pushed

Jul 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/diver-j/melgan-multi"

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