r9y9/jsut-lab

HTS-style full-context labels for JSUT v1.1

29
/ 100
Experimental

This provides detailed Japanese speech alignment files for the JSUT corpus, enabling speech researchers to develop and evaluate text-to-speech (TTS) and voice conversion systems. It takes raw JSUT audio and text data and outputs phonetic and prosodic labels with precise timing information. Speech scientists and engineers working on Japanese language synthesis or analysis would use these labels.

No commits in the last 6 months.

Use this if you are a speech researcher building or evaluating text-to-speech or voice conversion models for Japanese and need pre-processed, HTS-style labels for the JSUT corpus.

Not ideal if you require perfectly accurate, hand-annotated labels, as these are automatically generated and may contain errors.

Japanese speech synthesis voice conversion phonetic alignment speech research text-to-speech
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

51

Forks

2

Language

License

MIT

Last pushed

Apr 16, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/r9y9/jsut-lab"

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