listen-windy-nano

WindyWord.ai STT — Windy Nano

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

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

Profile

• Architecture: 39M params · whisper-tiny
• Profile: ultra-fast
• Base model: openai/whisper-tiny

Variants in this repo

Usage

from transformers import WhisperForConditionalGeneration, WhisperProcessor
processor = WhisperProcessor.from_pretrained("WindstormLabs/listen-windy-nano", subfolder="safetensors")
model = WhisperForConditionalGeneration.from_pretrained("WindstormLabs/listen-windy-nano", 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-tiny (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.