wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
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.
Stars
5,056
Forks
1,178
Language
Python
License
Apache-2.0
Category
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.
Related tools
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
sooftware/kospeech
Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.
hirofumi0810/neural_sp
End-to-end ASR/LM implementation with PyTorch