from transformers import WhisperProcessor, WhisperForConditionalGeneration
import torch

model = WhisperForConditionalGeneration.from_pretrained("rmtariq/whisper-RMTfinetuned")
processor = WhisperProcessor.from_pretrained("rmtariq/whisper-RMTfinetuned")

audio = "/path/to/audio.wav"
input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features

with torch.no_grad():
    predicted_ids = model.generate(input_features)

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