Next-gen Kaldi + WebAssembly Speech Enhancement with sherpa-onnx using GTCRN

Loading...

🎵 Input

Drop Audio Here (*.wav)

• or -
  Click to Upload

🎵 Output

Description

• Everything is open-sourced. code

• The model is from GTCRN

• Please upload .wav files

  • You can download noisy test wave files from https://htmlpreview.github.io/?https://github.com/Xiaobin-Rong/gtcrn_demo/blob/main/index.html

• If you have any issues, please either file a ticket or contact us via

  • WeChat group
  • QQ group
  • Bilibili

About This Demo

• Private and Secure: All processing is done locally on your device (CPU) within your browser with a single thread. No server is involved, ensuring privacy and security. You can disconnect from the Internet once this page is loaded.
• Efficient Resource Usage: No GPU is required, leaving system resources available for webLLM analysis.

Latest Update

• First working version.

Acknowledgement

• We refer to https://huggingface.co/spaces/Banafo/Kroko-Streaming-ASR-Wasm for the UI part.