English speech recognition model listen-windy-distil-large
Open speech-to-text model published by Windstorm Labs on Hugging Face.
- Task
- Speech-to-text (automatic speech recognition)
- Language
- English
- Lineage
- Distil-Whisper
- Formats in the repo
ct2-int8onnxonnx-int8safetensors- Hugging Face
- WindyWord/listen-windy-distil-large
- Last updated on HF
- 2026-08-05
Quality
Not benchmarked by this site yet. Speech models have no published word-error rates here; any figures in the Hugging Face card were not re-measured by us.
How to run
pip install transformers torch huggingface_hub # plus ffmpeg on your PATH to read audio filesfrom huggingface_hub import snapshot_download
from transformers import pipeline
# Weights live in the safetensors/ subfolder of the repository.
path = snapshot_download("WindyWord/listen-windy-distil-large", allow_patterns=["safetensors/*"])
asr = pipeline("automatic-speech-recognition", model=f"{path}/safetensors")
print(asr("audio.wav")["text"])Tested: Pattern run on 2026-10-01 against WindyWord/listen-windy-nano with transformers 4.57.6 and 5.18.0 on CPU, on a 16 kHz mono WAV. Not run on every model individually.
Licence and attribution
- Licence
- Apache-2.0 licence under review
- Upstream
- distil-whisper/distil-large-v3 (model card text)
- Upstream licence
- MIT
- Attribution
- Based on distil-whisper/distil-large-v3 (Distil-Whisper) by Hugging Face. Licensed MIT.
Under review: the Hugging Face card for this repository is tagged Apache-2.0, but its upstream (distil-whisper/distil-large-v3) is published under MIT. Until this is resolved, keep the upstream MIT terms and attribution with any copy you distribute.
Copy this into your NOTICE file (or equivalent) when you ship the model:
This product uses the model WindyWord/listen-windy-distil-large
(https://huggingface.co/WindyWord/listen-windy-distil-large), published by Windstorm Labs (https://windstormlabs.com).
Based on distil-whisper/distil-large-v3 (Distil-Whisper) by Hugging Face. Licensed MIT.
Redistributed by Windstorm Labs in additional formats; the model card states no fine-tuning was applied.
Licensed under the Apache License, Version 2.0: https://www.apache.org/licenses/LICENSE-2.0This is a convenience, not legal advice. See Licensing.