ayutaz/cc-g2pnp

Reimplementation of CC-G2PnP: Streaming Conformer-CTC based Japanese Grapheme-to-Phoneme and Prosody model (arXiv:2602.17157)

25
/ 100
Experimental

This project helps Japanese speech synthesis engineers and researchers convert written Japanese text into its phonetic pronunciation and prosody (rhythm and intonation) in real-time. It takes Japanese grapheme (written character) sequences as input and outputs phoneme and prosody symbol sequences, enabling the creation of more natural-sounding synthetic speech. This tool is for those working on Japanese text-to-speech (TTS) systems who need efficient and low-latency phonetic analysis.

Use this if you need to quickly and accurately convert Japanese text into its phonetic and prosodic representation for streaming speech synthesis applications.

Not ideal if you are working with languages other than Japanese, or if your primary need is for general text analysis rather than phonetic transcription.

Japanese-speech-synthesis text-to-speech phonetic-analysis prosody-modeling natural-language-processing
No License No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 3 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Python

License

Last pushed

Mar 08, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ayutaz/cc-g2pnp"

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