app.py

from flask import Flask, request, jsonify, render_template
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import torch
import torchaudio
import os

# Initialize Flask app
app = Flask(__name__)

# Load the model and processor
model_name = "jonatasgrosman/wav2vec2-large-xlsr-53-arabic"
processor = Wav2Vec2Processor.from_pretrained(model_name)
model = Wav2Vec2ForCTC.from_pretrained(model_name)

# Define the upload folder
UPLOAD_FOLDER = 'uploads'
app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER

# Ensure the upload folder exists
if not os.path.exists(UPLOAD_FOLDER):
    os.makedirs(UPLOAD_FOLDER)

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/transcribe', methods=['POST'])
def transcribe_audio():
    if 'file' not in request.files:
        return jsonify({'error': 'No file part'}), 400

    file = request.files['file']

    if file.filename == '':
        return jsonify({'error': 'No selected file'}), 400

    if file:
        # Save the uploaded file
        file_path = os.path.join(app.config['UPLOAD_FOLDER'], file.filename)
        file.save(file_path)

        # Load the audio file
        speech_array, sampling_rate = torchaudio.load(file_path)
        speech_array = torchaudio.transforms.Resample(orig_freq=sampling_rate, new_freq=16000)(speech_array)

        # Process the audio input
        input_values = processor(speech_array.squeeze().numpy(), return_tensors="pt", sampling_rate=16000).input_values

        # Perform inference
        with torch.no_grad():
            logits = model(input_values).logits

        # Get the predicted transcription
        predicted_ids = torch.argmax(logits, dim=-1)
        transcription = processor.batch_decode(predicted_ids)

        return jsonify({'transcription': transcription[0]})

    return jsonify({'error': 'Something went wrong!'}), 500

if __name__ == '__main__':
    app.run(debug=True)