# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("WindyWord/listen-windy-lingua-ar", device_map="auto")WindyWord.ai STT — Arabic Lingua (GPU (safetensors))
Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/listen-windy-lingua-ar
Transcribes Arabic speech (Afro-Asiatic > Semitic).
Quality
- WER: not yet measured by us. Imported from an upstream community fine-tune.
About this variant
This is the safetensors deployment format of our Arabic Lingua STT model. Load it via the safetensors/ subfolder.
Part of the WindyWord.ai STT fleet — covering 35+ languages that commercial speech-to-text APIs underserve, with proper dialect / script disclosures where they matter.
Usage
from transformers import WhisperForConditionalGeneration, WhisperProcessor
processor = WhisperProcessor.from_pretrained("WindyWord/listen-windy-lingua-ar", subfolder="safetensors")
model = WhisperForConditionalGeneration.from_pretrained("WindyWord/listen-windy-lingua-ar", subfolder="safetensors")
Apps
The Windy Word apps are built on this model family.
Provenance & License
Weights derived from Byne/whisper-large-v3-arabic (community fine-tune by Byne; identified from this repository's commit history and config.json). Licensed Apache-2.0 upstream; this redistribution is released under the same licence.
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="WindyWord/listen-windy-lingua-ar")