---
license: apache-2.0
tags:
- automatic-speech-recognition
- whisper
- windyword
- malayalam
- ml
library_name: transformers
pipeline_tag: automatic-speech-recognition
language:
- ml
---

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

**Transcribes Malayalam speech (Dravidian > Southern Dravidian).**

> **Note:** **Quality ceiling:** audited at 73.3% WER (community Malayalam Whisper space is thin — best alternative on HuggingFace audited at 76.5%, ~1.5% worse). Source: `vrclc/Whisper-small-Malayalam`. For high-stakes Malayalam transcription consider `openai/whisper-large-v3` multilingual.

## Quality

- **FLEURS WER:** 73.2% (50-sample audit)
- **CER:** 0.4872
- **Tier:** UNUSABLE-GAP ⭐
- **Source:** WindyWord Grand Rounds v2 audit (50-sample FLEURS)

## About this variant

This is the **safetensors** deployment format of our Malayalam 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-ml", subfolder="safetensors")
model = WhisperForConditionalGeneration.from_pretrained("WindyWord/listen-windy-lingua-ml", 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).*