On this page you can talk with an AI entity. It uses:
- OpenAI's Whisper model to listen to you as you speak in the microphone
- OpenAI's GPT-2 model to generate a text response
- Web Speech API to speak the response to you through the speakers
You can find more about this project on GitHub.
Whisper model:
GPT-2 model:
Status: idle
[The text context will be displayed here]
Debug output:
Troubleshooting
The page does some heavy computations, so make sure:
- To use a modern web browser (e.g. Chrome, Firefox)
- To use a fast desktop or laptop computer (e.g. not a mobile phone)
- Your browser supports WASM Fixed-width SIMD
|
Build time: |
Commit hash: @GIT_SHA1@ |
Commit subject: |
Source Code |