jinserk/pytorch-asr
ASR with PyTorch
This project helps speech recognition engineers and researchers experiment with different acoustic models for converting spoken audio into a sequence of phonemes. You provide recorded speech audio, and it outputs the phoneme sequence, which can then be used for further language model processing. It's designed for those who want to innovate on the 'acoustic' part of speech-to-text systems.
140 stars. No commits in the last 6 months.
Use this if you are a speech recognition researcher or engineer focusing on developing and testing new acoustic models that convert audio directly into phoneme sequences.
Not ideal if you need a complete, end-to-end speech-to-text solution that provides word-level transcriptions out-of-the-box without deep involvement in acoustic modeling.
Stars
140
Forks
20
Language
Python
License
GPL-3.0
Category
Last pushed
Mar 10, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jinserk/pytorch-asr"
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