Whisper Small fine-tuned for Roman-Urdu

This model is a fine-tuned version of openai/whisper-small for Roman-Urdu transcription.

Usage

from transformers import WhisperProcessor, WhisperForConditionalGeneration
import torch, librosa

model_id = "cheetos18/whisper-small-roman-urdu"
processor = WhisperProcessor.from_pretrained(model_id)
model = WhisperForConditionalGeneration.from_pretrained(model_id)

audio, sr = librosa.load("sample.wav", sr=16000)
inputs = processor(audio, sampling_rate=16000, return_tensors="pt")

with torch.no_grad():
    ids = model.generate(inputs.input_features)

print(processor.batch_decode(ids, skip_special_tokens=True)[0])