license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- whisper
- whisper.cpp
- ggml
- automatic-speech-recognition
- windyword
- mobile
- quantized
library_name: whisper.cpp
Windy Pro Engine — ggml q5_1 (mobile app shelf)
Promoted, not authored. This artifact was created in Windstorm Labs and pushed downstream unchanged. Do not edit weights here — fix them in the lab and re-promote, or this copy becomes a lie.
| File | ggml-windy-pro-engine-q5_1.bin |
| Size | 1177.0 MB |
| SHA-256 | 5a87af4730ddfb2ba13afeb4c8556a6c491fc831050a24b897117f44d2bc0618 |
| Quantization | q5_1 |
Provenance — one hop back
| Promoted from | WindyWord/windy-pro-engine-ggml |
| At revision | aca7f9832b0ce6c904861ac989c78fea4d4d56ca |
| Origin of record | WindstormLabs/windy-pro-engine-ggml @ f545eeab307893a2d25c0e98019bfc90837269b3 |
| Converted from | WindyWord/listen-windy-pro-engine @ d3035b10b7427db8efd3d73adf6b019347642705 |
Full chain: WindstormLabs -> WindyWord -> WindyWordMobileApp.
The SHA-256 above must match the lab's. If it does not, this copy has drifted.
Clinic patient file: sneakyfree/Windy-Clinic -> stt-models/windy-pro-engine.json
Licence
Upstream base is apache-2.0 on Hugging Face, verified against the source repo we converted from. Note OpenAI's Whisper GitHub repo states MIT while its HF model cards state Apache-2.0; we follow the HF distribution point, since that is what we actually pulled. Windy weights are a derivative and are distributed under the same terms, with attribution upstream.