CoolFace
Modelpublic

wabisabisocial/whisper-tiny-spanish-ggml

sourceHugging Faceapache-2.0updated 7mo agoView on Hugging Face
0likes
Model Card

whisper-tiny-spanish-ggml

GGML conversion of arpagon/whisper-tiny-es for use with whisper.cpp

Original Model

This is a GGML-converted version of arpagon/whisper-tiny-es.

Original model credit: arpagon/whisper-tiny-es

All credit for the fine-tuning work goes to the original authors. This repository only provides the GGML conversion for use with whisper.cpp and mobile applications.

Model Details

  • —Base Model: OpenAI Whisper Base
  • —Format: GGML (whisper.cpp compatible)
  • —Language: es
  • —File Size: 74.09 MB
  • —Model File: ggml-tiny-es.bin
  • —Conversion: Converted using whisper.cpp's convert-h5-to-ggml.py

Usage

With whisper.cpp

bash
# Clone whisper.cpp
git clone https://github.com/ggerganov/whisper.cpp
cd whisper.cpp

# Build
make

# Download this model
wget https://huggingface.co/wabisabisocial/whisper-tiny-spanish-ggml/resolve/main/ggml-tiny-es.bin

# Run transcription
./main -m ggml-tiny-es.bin -f audio.wav -l es

With React Native (whisper.rn)

typescript
import WhisperContext from 'whisper.rn';

const context = await WhisperContext.initWithUrl(
  'https://huggingface.co/wabisabisocial/whisper-tiny-spanish-ggml/resolve/main/ggml-tiny-es.bin'
);

const { result } = await context.transcribe(audioPath, {
  language: 'es',
});

Direct Download

bash
wget https://huggingface.co/wabisabisocial/whisper-tiny-spanish-ggml/resolve/main/ggml-tiny-es.bin

Performance

For performance metrics and evaluation results, please refer to the original model.

License

This model is released under the Apache 2.0 License, matching the original model's license.

Per Apache 2.0 requirements:

  • —✅ Commercial use allowed
  • —✅ Modification allowed
  • —✅ Distribution allowed
  • —⚠️ Must include attribution to original authors
  • —⚠️ Must include copy of license

Citation

If you use this model, please cite both the original model and OpenAI Whisper:

bibtex
@misc{whisper-es-ggml-wabisabisocial,
  author = {wabisabisocial},
  title = {whisper-tiny-spanish-ggml},
  year = {2026},
  publisher = {Hugging Face},
  note = {GGML conversion of arpagon/whisper-tiny-es},
  howpublished = {\url{https://huggingface.co/wabisabisocial/whisper-tiny-spanish-ggml}}
}

@article{radford2022whisper,
  title = {Robust Speech Recognition via Large-Scale Weak Supervision},
  author = {Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
  journal = {arXiv preprint arXiv:2212.04356},
  year = {2022}
}

Acknowledgments