surah-kawthar-asr-v2

Surah Al-Kawthar ASR Model

This is a fine-tuned Wav2Vec2ForCTC model for Arabic (Quranic) speech recognition — specifically Surah Al-Kawthar recitations.

Example usage (Python)

from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import torch, soundfile as sf

processor = Wav2Vec2Processor.from_pretrained("shani925273/surah-kawthar-asr-v2")
model = Wav2Vec2ForCTC.from_pretrained("shani925273/surah-kawthar-asr-v2")

audio, rate = sf.read("sample.wav")
inputs = processor(audio, sampling_rate=16000, return_tensors="pt", padding=True)

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

predicted_ids = torch.argmax(logits, dim=-1)
text = processor.batch_decode(predicted_ids)[0]
print(text)