from transformers import AutoModelForCTC, Wav2Vec2Processor
import torch
import librosa

# Load model and processor
model = AutoModelForCTC.from_pretrained("Mathur08/autotrain-mfnfj-9bczx")
processor = Wav2Vec2Processor.from_pretrained("Mathur08/autotrain-mfnfj-9bczx")

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

with torch.no_grad():
    logits = model(inputs.input_values).logits
    predicted_ids = torch.argmax(logits, dim=-1)
    transcription = processor.batch_decode(predicted_ids)