FocsleFocsle
HE

Distil-Whisper-Tiny

1%
by HuggingFace-Edge

HF-Edge distillation. Good multilingual coverage on the higher-power tier.

Embedded ASRMITINT8FP16multilingualasr
268K downloads 14K deploymentsUpdated Jan 6, 2028
Headline:92ms · Snapdragon 8 Gen 3 NPU · INT8

Deploy Distil-Whisper-Tiny

Pick a chip family. We hand you the artifacts (HEF, TRT engine, Core ML, ONNX) plus a one-click endpoint deploy. For private endpoints, on-prem deploy, or air-gapped distribution, see Enterprise.

QQualcomm QCS8550
# QNN / Hexagon
$ focsle pull huggingface-edge/distil-whisper-tiny --target qnn-qcs8550
$ focsle compile distil-whisper-tiny.onnx --target qnn --quant int8

# Run via QNN backend
import focsle.runtime as fr
m = fr.load("distil-whisper-tiny.qnn.bin", target="qnn")
out = m.run(frame)

One-click endpoint

Spins up a managed endpoint in the closest region. Pro and above.

Or deploy yourself