jzmzhong/Automatic-Prosody-Annotator-with-SSWP-CLAP

An automatic prosodic boundary annotation tool for Text-to-Speech Synthesis (TTS).

27
/ 100
Experimental

This tool helps Text-to-Speech (TTS) developers and researchers automatically mark prosodic boundaries in speech data. It takes aligned text and audio features as input and outputs precise annotations for where 'prosodic words' and 'prosodic phrases' occur. This is essential for creating more natural and controllable synthetic speech.

No commits in the last 6 months.

Use this if you are a Text-to-Speech developer or researcher who needs to automatically annotate large amounts of speech data with prosodic boundaries to improve speech synthesis quality.

Not ideal if you are looking for a general-purpose audio transcription or natural language processing tool not specifically focused on prosody for TTS.

text-to-speech speech-synthesis prosody-annotation computational-linguistics voice-AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 3 / 25

How are scores calculated?

Stars

51

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Jun 11, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jzmzhong/Automatic-Prosody-Annotator-with-SSWP-CLAP"

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