IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53

from transformers import pipeline

asr = pipeline("automatic-speech-recognition", model="IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53")
asr("path/to/audio.wav")

# Long-Form Transcription: https://huggingface.co/blog/asr-chunking
asr = pipeline("automatic-speech-recognition", model="IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53", chunk_length_s=30) 
asr("path/to/audio.wav")

from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import torch
import torchaudio

model = Wav2Vec2ForCTC.from_pretrained("IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53")
processor = Wav2Vec2Processor.from_pretrained("IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53")

# Load audio (must be mono, 16kHz)
waveform, sr = torchaudio.load("path/to/audio.wav")

# Convert to mono if not already
if waveform.shape[0] > 1:
    waveform = torch.mean(waveform, dim=0, keepdim=True)

# Resample if needed to 16 kHz
if sr != 16000:
    resampler = torchaudio.transforms.Resample(orig_freq=sr, new_freq=16000)
    waveform = resampler(waveform)

inputs = processor(waveform.squeeze(), sampling_rate=16000, return_tensors="pt")

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

predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(predicted_ids)
print(transcription)

import torch
import torchaudio
import re
from datasets import load_dataset
from evaluate import load
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor

# Device setup
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

# 🔑 Replace with your Hugging Face token and the desired Wav2Vec2-based model ID
HF_TOKEN = "your_hf_token"
MODEL_NAME = "your_model_name_or_path"

# Load the Common Voice 17.0 Arabic test split
test_dataset = load_dataset(
    "mozilla-foundation/common_voice_17_0", 
    "ar", 
    split="test", 
    token=HF_TOKEN
)

# Load WER metric
wer = load("wer")

# Load processor and model
processor = Wav2Vec2Processor.from_pretrained(MODEL_NAME, token=HF_TOKEN)
model = Wav2Vec2ForCTC.from_pretrained(MODEL_NAME, token=HF_TOKEN).to(device)

# Define regex for cleaning up unwanted characters
CHARS_TO_IGNORE_REGEX = r'[\؛\—\_get\«\»\ـ\,\?\.\!\-\;\:"\“\%\‘\”\�\#\،\☭,\؟]'

def preprocess(batch):
    """Removes unwanted characters and resamples audio to 16kHz."""
    batch["sentence"] = re.sub(CHARS_TO_IGNORE_REGEX, "", batch["sentence"])
    speech_array, sampling_rate = torchaudio.load(batch["path"])
    resampler = torchaudio.transforms.Resample(orig_freq=sampling_rate, new_freq=16_000)
    batch["speech"] = resampler(speech_array).squeeze().numpy()
    return batch

# Apply preprocessing
test_dataset = test_dataset.map(preprocess)

def predict(batch):
    """Runs inference and decodes predicted text."""
    inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
    
    with torch.inference_mode():
        logits = model(
            input_values=inputs["input_values"].to(device), 
            attention_mask=inputs["attention_mask"].to(device)
        ).logits

    predicted_ids = torch.argmax(logits, dim=-1)
    batch["pred_strings"] = processor.batch_decode(predicted_ids)
    return batch

# Run prediction
result = test_dataset.map(predict, batched=True, batch_size=8)

# Compute and print Word Error Rate
wer_score = wer.compute(predictions=result["pred_strings"], references=result["sentence"])
print(f"WER: {wer_score * 100:.2f}%")

@misc{amin2025egyptianasr,
  title={Egyptian Arabic ASR with wav2vec2 XLSR 53},
  author={Ibrahim Amin},
  year={2025},
  howpublished={\url{https://huggingface.co/IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53}},
}