Bengali Whisper LoRA
Fine-tuned on Dummy (Testing).
Usage
from transformers import pipeline
pipe = pipeline("automatic-speech-recognition", model="Tmanna/bengali-whisper-pro")
result = pipe("audio.wav")
print(result["text"])
Details
- Base: openai/whisper-tiny
- LoRA: r=16, alpha=32
- Samples: 45
