tabahi/contexless-phonemes-CUPE

pytorch model for contexless-phoneme prediction from speech audio

39
/ 100
Emerging

This project helps speech researchers and phoneticians analyze speech audio by extracting individual phonemes without considering the surrounding sounds. It takes an audio file (like a WAV) as input and outputs a sequence of predicted phonemes and phoneme groups for each 120ms slice of sound. Linguists, speech pathologists, and anyone studying the fine-grained acoustic properties of speech would find this useful.

Use this if you need to understand the distinct acoustic properties of individual sound units (phonemes) within speech, independent of their context.

Not ideal if your task requires understanding how phonemes change based on surrounding words or sounds, as this tool specifically ignores context.

speech-analysis phonetics linguistics audio-research speech-pathology
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 11 / 25

How are scores calculated?

Stars

32

Forks

4

Language

Python

License

GPL-3.0

Last pushed

Oct 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/tabahi/contexless-phonemes-CUPE"

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