wabisabisocial/whisper-tiny-spanish-ggml
0
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
# 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 esWith React Native (whisper.rn)
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
wget https://huggingface.co/wabisabisocial/whisper-tiny-spanish-ggml/resolve/main/ggml-tiny-es.binPerformance
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:
@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
- Original Whisper model: OpenAI Whisper
- GGML conversion tools: whisper.cpp
- Fine-tuned model: arpagon/whisper-tiny-es
