sooftware/lightning-asr

Modular and extensible speech recognition library leveraging pytorch-lightning and hydra.

36
/ 100
Emerging

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.

speech-recognition ASR-research deep-learning-research audio-processing AI-model-training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

50

Forks

6

Language

Python

License

MIT

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.