---
license: apache-2.0
tags:
- automatic-speech-recognition
- whisper
- windyword
- igbo
- ig
library_name: transformers
pipeline_tag: automatic-speech-recognition
language:
- ig
---

# WindyWord.ai STT — Igbo Lingua (GPU (safetensors))

**Transcribes Igbo speech (Niger-Congo > Volta-Niger).**

> **Note:** **Quality caveat:** model is whisper-tiny-igbo (39M params, 4 layers); audited at 157% WER. Limited capacity at this parameter size; for production use we recommend an `openai/whisper-large-v3` multilingual fallback.

## Quality

- **FLEURS WER:** 157.4% (50-sample audit)
- **CER:** 1.5418
- **Tier:** UNUSABLE-GAP ⭐
- **Source:** WindyWord Grand Rounds v2 audit (50-sample FLEURS)

## About this variant

This is the **safetensors** deployment format of our Igbo Lingua STT model. Load it via the `safetensors/` subfolder.

Part of the [WindyWord.ai](https://windyword.ai) STT fleet — covering 35+ languages that commercial speech-to-text APIs underserve, with proper dialect / script disclosures where they matter.

## Usage

```python
from transformers import WhisperForConditionalGeneration, WhisperProcessor
processor = WhisperProcessor.from_pretrained("WindyWord/listen-windy-lingua-ig", subfolder="safetensors")
model = WhisperForConditionalGeneration.from_pretrained("WindyWord/listen-windy-lingua-ig", subfolder="safetensors")
```

## Commercial Use

Visit [windyword.ai](https://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).*