Menhaz/distil-whisper-torgo-dysarthric

distil-whisper fine-tuned on TORGO (Dysarthric Speech)

Fine-tuned from distil-whisper/distil-large-v3 on the TORGO dysarthric speech corpus. Only dysarthric speakers were used for training and evaluation.

Usage

from transformers import pipeline

pipe = pipeline(
    "automatic-speech-recognition",
    model="Menhaz/distil-whisper-torgo-dysarthric",
)
result = pipe("your_audio.wav")
print(result["text"])