HoseinAzad/SpeechT5-Non-English-TTS

Fine-tune SpeechT5 for non-English text-to-speech task, implemented in PyTorch.

26
/ 100
Experimental

This project helps developers create custom text-to-speech systems for languages other than English. You provide text data and corresponding audio samples in your desired language, and it outputs a specialized speech model that can convert new text into natural-sounding speech. This is for AI/ML developers or researchers who need to build advanced speech synthesis capabilities for specific non-English languages.

No commits in the last 6 months.

Use this if you are a machine learning engineer looking to fine-tune a powerful SpeechT5 model to generate high-quality spoken audio from text in a non-English language.

Not ideal if you need an out-of-the-box text-to-speech solution without deep technical setup or if your target language is already well-supported by existing models.

speech-synthesis natural-language-processing machine-learning-engineering audio-generation AI-development
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

8

Forks

3

Language

Python

License

Last pushed

May 28, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/HoseinAzad/SpeechT5-Non-English-TTS"

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