Home / Speech / windy-core-ggml

Multilingual speech recognition model windy-core-ggml

Open speech-to-text model published by Windstorm Labs on Hugging Face.

Task: Speech-to-text (automatic speech recognition)
Language: Multilingual (the Whisper language set)
Lineage: Whisper
Formats in the repo: ggml
Converted from: WindyWord/listen-windy-core
Hugging Face: WindyWord/windy-core-ggml
Last updated on HF: 2026-08-01

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

Shell

# build whisper.cpp from https://github.com/ggml-org/whisper.cpp, then:
pip install huggingface_hub

Shell

# Not tested by this site. Download the single model file, then run whisper.cpp:
hf download WindyWord/windy-core-ggml ggml-windy-core-q5_1.bin --local-dir .
./build/bin/whisper-cli -m ggml-windy-core-q5_1.bin -f audio.wav

Untested: this snippet has not been run by us. Treat it as a starting point.

Licence and attribution

Licence: Apache-2.0
Upstream: openai/whisper-small
Upstream licence: Apache-2.0
Attribution: Based on openai/whisper-small (Whisper) by OpenAI. Licensed Apache-2.0.

Copy this into your NOTICE file (or equivalent) when you ship the model:

NOTICE

This product uses the model WindyWord/windy-core-ggml
(https://huggingface.co/WindyWord/windy-core-ggml), published by Windstorm Labs (https://windstormlabs.com).
Based on openai/whisper-small (Whisper) by OpenAI. Licensed Apache-2.0.
Converted by Windstorm Labs to ggml (q5_1) from WindyWord/listen-windy-core.
Licensed under the Apache License, Version 2.0: https://www.apache.org/licenses/LICENSE-2.0

This is a convenience, not legal advice. See Licensing.