SeanPLeary/dc_tts-transfer-learning

Transfer learning exploration of dc_tts text-to-speech model

30
/ 100
Emerging

This project explores how to adapt an existing AI-powered voice to a new voice with minimal new data, rather than building a new voice from scratch. You provide a small amount of new voice recordings, and the system modifies a pre-trained voice model to sound like your new speaker, generating high-quality speech from text. This is useful for content creators, game developers, or anyone needing to generate custom speech in a specific voice efficiently.

No commits in the last 6 months.

Use this if you want to create a text-to-speech system for a new voice using a small dataset, leveraging an existing, high-quality base voice model.

Not ideal if you need to build a text-to-speech model from scratch for a new language or without any pre-existing voice models.

voice-cloning audio-production synthetic-media content-creation voiceover
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

21

Forks

7

Language

Python

License

Last pushed

Mar 05, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/SeanPLeary/dc_tts-transfer-learning"

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