What it does
WeNet converts spoken audio into written text. It is designed for use in real products, and covers everything from training models to running them.
It comes with ready-made models, including several for Chinese and Whisper models for English. You can run it from the command line on an audio file or use it in Python code.
Its makers say it is accurate on many public speech datasets, light, and easy to install.
Who it's for
Developers and researchers building speech-to-text features, especially for Chinese and English.
Can I use it without coding?
With some setup. You install it with Python and run it by typing a command. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Computer
- An ordinary computer is fine
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
- Install Python, then install WeNet using Python's package installer.
- Run WeNet on an audio file, choosing a Chinese model or a Whisper model for English.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- WeNet 2.0: More Productive End-to-End Speech Recognition ToolkitResearch paper · Mar 2022