Official documentation
Transformers.js README (Hugging Face)
Hugging Face, GitHub, 2026
Read the originalRead on October 17, 2026
- What it is
- The project's own README for Transformers.js, a JavaScript library that runs machine learning models, including Whisper speech recognition models, inside a web page. It says that models run on the CPU through WebAssembly by default and on the GPU through WebGPU when set.
- How much weight it carries
- The official project documentation, maintained by Hugging Face. It describes the default and the option, but not speed on any particular computer, so benchmarks must come from other sources.
Facts taken from this source
- Transformers.js runs a model on the CPU through WebAssembly by default in the browser, and on the GPU through WebGPU only when the page sets the device option.
“By default, when running in the browser, the model will be run on your CPU (via WASM). If you would like to run the model on your GPU (via WebGPU), you can do this by setting `device: 'webgpu'`” (Device section)