CoolFace
Modelpublic

Africanvoice/african_voices_large_yoruba

sourceHugging Faceapache-2.0updated 4d agoView on Hugging Face
0likes35downloads
Model Card

Whisper Large Model finetuned using African Voices Yoruba Dataset

This model is a fine-tuned version of openai/whisper-large-v3 for Yoruba Language.

Model Description

Whisper Large Model finetuned using African Voices Yoruba Dataset is an automatic speech recognition (ASR) model trained on Africanvoice/African_voices_yoruba dataset.

Performance

  • —eval_loss: 0.22
  • —WER: 30.02%

Training Details

  • —Epochs: 4
  • —Batch Size: 16
  • —Learning Rate: 7e-6

Usage

python
from transformers import pipeline

# Load the model
pipe = pipeline("automatic-speech-recognition", model="Africanvoice/african_voices_large_yoruba")

# Transcribe audio
result = pipe("path/to/audio.wav")
print(result["text"])

Citation

If you use this model, please cite:

bibtex
@misc{Whisper Large Model finetuned using African Voices Yoruba Dataset,
  author = {EqualyzAI and African Voices Team},
  title = {Whisper Large Model finetuned using African Voices Yoruba Dataset},
  year = {2025},
  publisher = {HuggingFace},
  howpublished = {\url{https://huggingface.co/Africanvoice/african_voices_large_yoruba}}
}