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
Source Model: APACHE-2.0
Deployable Model: APLUX-MODEL-FARM-LICENSE