tabahi/contexless-phonemes-CUPE
pytorch model for contexless-phoneme prediction from speech audio
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.
Stars
32
Forks
4
Language
Python
License
GPL-3.0
Category
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.
Higher-rated alternatives
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
srvk/eesen
The official repository of the Eesen project