wenet-e2e/wenet
An end-to-end speech recognition toolkit providing production-ready ASR models including Paraformer, Whisper, and Conformer architectures.
Not currently ranked — collecting fresh signals.
star history
WeNet is a production-oriented end-to-end speech recognition toolkit built on PyTorch. It provides training, inference, and deployment pipelines for various ASR architectures including Conformer and Transformer models, with support for pretrained models like Whisper. The toolkit includes both Python package and command-line interfaces for transcribing audio, and offers runtime solutions for production deployment.
Frequently asked
- What is wenet-e2e/wenet?
- An end-to-end speech recognition toolkit providing production-ready ASR models including Paraformer, Whisper, and Conformer architectures.
- Is wenet open source?
- Yes — wenet-e2e/wenet is open source, released under the Apache-2.0 license.
- What language is wenet written in?
- wenet-e2e/wenet is primarily written in Python.
- How popular is wenet?
- wenet-e2e/wenet has 5.2k stars on GitHub.
- Where can I find wenet?
- wenet-e2e/wenet is on GitHub at https://github.com/wenet-e2e/wenet.