stt-1b-en_fr-q4_0-webgpu

Q4-quantized weights for a ~1B-parameter streaming speech-to-text transformer, packaged for the browser.

kyutai/stt-1b-en_fr, by Kyutai

Q4_0 quantization for WebGPU by Idle Intelligence.

CC-BY-4.0

Q4-quantized weights for kyutai/stt-1b-en_fr, packaged for client-side browser inference via WASM + WebGPU: English and French, streaming, about 1B parameters. Consumed by stt-web; not affiliated with or endorsed by Kyutai Labs.

Type
model
Runs
browser, WASM, WebGPU
Size
~1B + ~25M params, 638MB total (Q4_0 + f16)
Demo (GitHub Pages)
https://idle-intelligence.github.io/stt-web/web/
Source
idle-intelligence/stt-web
HuggingFace
idle-intelligence/stt-1b-en_fr-q4_0-webgpu
Status
maintained

Used on: stt

← Home