MahtaFetrat/LLM-Powered-G2P

Code and Resources for "LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study", introducing methods to leverage LLMs for G2P tasks without additional training, featuring Sentence-Bench and Kaamel-Dict.

32
/ 100
Emerging

This project helps speech processing engineers and linguists accurately convert written words (graphemes) into their spoken sounds (phonemes), especially for text-to-speech systems. It takes written text, even complex cases like homographs, and produces precise phonetic transcriptions. This is particularly useful for developing speech applications in languages like Persian.

No commits in the last 6 months.

Use this if you need to convert written text into its phonetic pronunciation for speech synthesis, especially in languages with complex pronunciation rules or when traditional G2P tools struggle with context-dependent words.

Not ideal if you only need basic, rule-based grapheme-to-phoneme conversion for widely supported languages where context and homographs are not a significant concern.

speech-synthesis text-to-speech linguistics persian-language phonetics
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

20

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

May 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/MahtaFetrat/LLM-Powered-G2P"

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