license: apache-2.0
tags:
- automatic-speech-recognition
- whisper
- windyword
- german
- de
library_name: transformers
pipeline_tag: automatic-speech-recognition
language:
- de
WindyWord.ai STT — German Lingua (GPU (safetensors))
Transcribes German speech (Indo-European > Germanic > West Germanic).
Note: Standard High German (Hochdeutsch). Indo-European > Germanic > West Germanic. Derived from
primeline/whisper-large-v3-turbo-german— the top community German Whisper fine-tune (46k+ downloads). Replaces an earlier Swiss-German-only variant. WER 42.6% / CER 8.06% on 100-sample FLEURS (CER is the reliable signal here).
Quality
- FLEURS WER: 56.7% (50-sample audit)
- CER: 0.2748
- Tier: UNUSABLE-GAP ⭐
- Source: WindyWord Grand Rounds v2 audit (50-sample FLEURS)
About this variant
This is the safetensors deployment format of our German 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-de", subfolder="safetensors")
model = WhisperForConditionalGeneration.from_pretrained("WindyWord/listen-windy-lingua-de", subfolder="safetensors")
Commercial Use
Visit windyword.ai for apps and API access.
Provenance & License
Weights derived from upstream community Whisper fine-tunes (see individual model card for exact lineage). Redistributed under Apache-2.0 (inherited).
Certified by Opus 4.6 Opus-Claw (Dr. C) on Veron-1 (RTX 5090, Mt Pleasant SC).