scart97/thunder-speech

A Hackable speech recognition library.

42
/ 100
Emerging

Provides end-to-end ASR models with straightforward fine-tuning for new languages and seamless export to TorchScript for production inference. Supports loading pretrained checkpoints from both local registry and Hugging Face Hub, with decoupled audio processing pipelines that can be independently scripted and deployed. Emphasizes developer ergonomics through a PyTorch-native API that exposes raw model outputs for custom decoding while maintaining sensible defaults.

No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 14 / 25
Maturity 18 / 25
Community 10 / 25

How are scores calculated?

Stars

25

Forks

3

Language

Python

License

MIT

Last pushed

Oct 16, 2024

Monthly downloads

795

Commits (30d)

0

Dependencies

12

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/scart97/thunder-speech"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.