wav2vec2-large-xlsr-53-arabic-quran-v_final

from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import torch
import librosa

model_id = "rabah2026/wav2vec2-large-xlsr-53-arabic-quran-v_final"

processor = Wav2Vec2Processor.from_pretrained(model_id)
model = Wav2Vec2ForCTC.from_pretrained(model_id)

# Chargement audio (16kHz obligatoire)
audio, sr = librosa.load("verset.mp3", 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, skip_special_tokens=True)[0]

print(transcription)