Downloads · 30 days
0
listen-windy-edge
WindstormLabs/listen-windy-edge
listen-windy-edge is a automatic speech recognition model from WindstormLabs. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as mit.
Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/listen-windy-edge
Access
Public
Updated Oct 1, 2026
Repo size
8.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx_data5.1 GB · 45%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- mit
- Access
- Public
- Created
- May 19, 2026
- Updated
- Oct 1, 2026
- SHA
- b022cc5e
Base models
Model card
From the Hugging Face model README
WindyWord.ai STT — Windy Edge
Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/listen-windy-edge
Multilingual speech-to-text engine. Transcribes audio in 100+ languages, with English as the primary trained domain.
Profile
- Architecture: 756M params · distil-whisper-large-v3
- Profile: edge / mobile
- Base model: distil-whisper/distil-large-v3
Variants in this repo
| Subfolder | Format | Use case |
|---|---|---|
safetensors/ | PyTorch safetensors (FP32) | GPU inference (highest quality) |
ct2-int8/ | CTranslate2 INT8 | CPU inference (~25% size, 2-4× faster) |
onnx/ | ONNX FP32 | Cross-platform deployment |
onnx-int8/ | ONNX INT8 | Edge / mobile / WebAssembly |
Usage
from transformers import WhisperForConditionalGeneration, WhisperProcessor
processor = WhisperProcessor.from_pretrained("WindstormLabs/listen-windy-edge", subfolder="safetensors")
model = WhisperForConditionalGeneration.from_pretrained("WindstormLabs/listen-windy-edge", subfolder="safetensors")
For CPU inference via CTranslate2:
import ctranslate2
# After downloading the ct2-int8 subfolder:
model = ctranslate2.models.Whisper("path/to/ct2-int8/")
Apps
The Windy Word apps are built on this model family.
Provenance & License
Weights derived from distil-whisper/distil-large-v3 (Distil-Whisper, Hugging Face), licensed MIT. Windy variants are released under the same licence. Voice tiers are direct redistributions of the upstream community Whisper / distil-whisper variants; no LoRA fine-tuning has been applied to these voice models.
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- mit
- Languages
- en, multilingual
- Created
- May 19, 2026
- Updated
- Oct 1, 2026