bench : Benchmark whisper.cpp performance in the browser

You can find more about this project on GitHub.

More examples: main | bench | stream | command |


Select the model you would like to use and click the "Bench" button.
The results will be displayed in the textarea below.

Whisper model:

Quantized models:



Debug output:
Troubleshooting

The page does some heavy computations, so make sure:
| Build time: Mon May 26 01:57:39 2025 | Commit hash: ea9f206f | Commit subject: talk-llama : fix for swedish umlauts + expose model inference settings in talk-llama.cpp (#3187) | Source Code |