import torch
import librosa
from transformers import AutoModelForCTC, AutoProcessor

model_id = "abiawilliamsa/Akan-ASR-AAW-0.2387"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForCTC.from_pretrained(model_id)

# Load audio (16kHz)
audio, sr = librosa.load("sample_akan.wav", sr=16000)
inputs = processor(audio, sampling_rate=16000, return_tensors="pt")

with torch.no_grad():
    logits = model(**inputs).logits

predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(predicted_ids)[0]
print("Transcription:", transcription)