WeNet: ASR

WeNet is an open-source end-to-end (E2E) automatic speech recognition (ASR) model designed to provide efficient, accurate, and flexible speech recognition capabilities. Developed by Tencent AI Lab, WeNet achieves a unified architecture between streaming and non-streaming recognition. It adopts the U2++ (Unified Streaming and Non-streaming Model) framework, enabling both real-time streaming recognition and high-precision offline recognition, while avoiding the complexity of training separate models for streaming and non-streaming ASR in traditional approaches.

Source model

  • Input shape: Dynamic input
  • Number of parameters: --,--
  • Model size: 365M
  • Output shape: Dynamic output

The source model can be found here

Performance Reference

Please search model by model name in Model Farm

Inference & Model Conversion

Please search model by model name in Model Farm

License

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support