Wav2vec Test

🚀 Test Wav2Vec2 with Egyptian Arabic

This project fine - tunes the facebook/wav2vec2-large-xlsr-53 model in Egyptian Arabic using the arabicspeech.org MGB-3. It provides a solution for automatic speech recognition in Egyptian Arabic.

🚀 Quick Start

When using this model, make sure that your speech input is sampled at 16kHz.

✨ Features

• Fine - tuned on Egyptian Arabic using the arabicspeech.org MGB-3 dataset.
• Can be used directly without a language model.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

import torch
import torchaudio
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
dataset = load_dataset("arabic_speech_corpus", split="test")
processor = Wav2Vec2Processor.from_pretrained("othrif/wav2vec_test")
model = Wav2Vec2ForCTC.from_pretrained("othrif/wav2vec_test")
resampler = torchaudio.transforms.Resample(48_000, 16_000)
# Preprocessing the datasets.
# We need to read the aduio files as arrays
def speech_file_to_array_fn(batch):
    speech_array, sampling_rate = torchaudio.load(batch["path"])
    batch["speech"] = resampler(speech_array).squeeze().numpy()
    return batch
test_dataset = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
with torch.no_grad():
    logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
predicted_ids = torch.argmax(logits, dim=-1)
print("Prediction:", processor.batch_decode(predicted_ids))
print("Reference:", test_dataset["sentence"][:2])

📚 Documentation

Model Information

Results

The model has the following performance on the arabicspeech.org MGB-3 dataset:

🔧 Technical Details

No technical details are provided in the original document, so this section is skipped.

📄 License

This project is licensed under the Apache 2.0 license.