openspeech-team/openspeech
Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.
This is a toolkit for machine learning engineers and researchers to build custom automatic speech recognition (ASR) systems. It allows you to feed audio recordings and receive transcribed text, using a simplified training process for cutting-edge models. The ideal users are those who need to develop or experiment with advanced speech-to-text models for specific applications or languages.
718 stars. No commits in the last 6 months.
Use this if you are an AI/ML engineer or researcher looking to train your own end-to-end speech recognition models with powerful features like multi-GPU training and mixed precision.
Not ideal if you need a ready-to-use API for speech-to-text conversion or pre-trained models, as this framework focuses on model development rather than deployment.
Stars
718
Forks
114
Language
Python
License
MIT
Category
Last pushed
Oct 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/openspeech-team/openspeech"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
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