WindstormLabs/listen-windy-pro-engine

WindyWord.ai STT — Windy Pro Engine

Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/listen-windy-pro-engine

Multilingual speech-to-text engine. Transcribes audio in 100+ languages, with English as the primary trained domain.

Profile

• Architecture: 1.55B params · whisper-large-v3
• Profile: premium / max accuracy
• Base model: openai/whisper-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-pro-engine", subfolder="safetensors")
model = WhisperForConditionalGeneration.from_pretrained("WindstormLabs/listen-windy-pro-engine", 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 openai/whisper-large-v3 (OpenAI Whisper), licensed Apache-2.0. 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.