wenet-e2e/wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit

57
/ 100
Established

Supports both streaming and non-streaming decoding with unified architecture, plus language model integration via WFST graphs for improved accuracy. Built on PyTorch with native support for Ascend NPU acceleration alongside CUDA, and includes pre-trained models (Paraformer, Whisper) accessible via simple pip install or Python API. Provides full runtime stack for x86 deployment with optional libtorch-based inference engine.

5,056 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

5,056

Forks

1,178

Language

Python

License

Apache-2.0

Last pushed

Dec 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/wenet-e2e/wenet"

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