yl4579/AuxiliaryASR

Joint CTC-S2S Phoneme-level ASR for Voice Conversion and TTS (Text-Mel Alignment)

48
/ 100
Emerging

This project helps researchers and developers in speech technology fine-tune or train an Automatic Speech Recognition (ASR) model specifically for voice conversion and text-to-speech applications. It takes audio recordings with corresponding text labels and speaker information as input, producing a specialized ASR model that accurately aligns phonemes with audio. This is ideal for those working on synthesizing realistic speech or transforming voices.

125 stars. No commits in the last 6 months.

Use this if you need to train a phoneme-level ASR model to precisely align audio with text for advanced voice conversion or text-to-speech systems.

Not ideal if you're looking for a general-purpose, off-the-shelf ASR solution for transcribing speech or command and control applications.

voice-synthesis voice-conversion text-to-speech speech-technology phoneme-alignment
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

125

Forks

48

Language

Python

License

MIT

Last pushed

Jun 16, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/yl4579/AuxiliaryASR"

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