sooftware/lightning-asr
Modular and extensible speech recognition library leveraging pytorch-lightning and hydra.
This project helps speech recognition researchers train sophisticated speech-to-text models more efficiently. It takes audio data (like speech recordings) and model configurations as input to produce a trained ASR model. Researchers focused on building and refining automatic speech recognition systems for various applications would find this useful.
No commits in the last 6 months.
Use this if you are a researcher developing advanced speech recognition models and need to streamline your training workflow, especially when dealing with complex setups like multi-GPU or 16-bit precision.
Not ideal if you are a practitioner looking for a ready-to-use speech-to-text API or a pre-trained model without getting involved in model architecture and training specifics.
Stars
50
Forks
6
Language
Python
License
MIT
Category
Last pushed
May 19, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/sooftware/lightning-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