Dragneel/whisper-small-nepali-openslr

Whisper Small Fine-tuned on Nepali (OpenSLR 54)

This model is a fine-tuned version of openai/whisper-small on the OpenSLR 54 (Nepali Speech Corpus) dataset.

Model Details

• Model: Whisper Small (244M Parameters)
• Dataset: ~154 Hours of Nepali Audio
• Language: Nepali
• Hardware: NVIDIA A100 80GB

Results

• WER: 26.69%
• Loss: 0.210

Usage

from transformers import pipeline

transcriber = pipeline(
    "automatic-speech-recognition", 
    model="Dragneel/whisper-small-nepali-openslr"
)

text = transcriber("path_to_audio.mp3")
print(text["text"])