main.py

from flask import Flask, request, jsonify
import whisper
import tempfile
import os
from pathlib import Path
import torch
from flask_cors import CORS

app = Flask(__name__)
CORS(app)

# Load Whisper model
model = whisper.load_model("base")

@app.route('/transcribe', methods=['POST'])
def transcribe_audio():
    try:
        # Check if audio file is in the request
        if 'audio' not in request.files:
            return jsonify({'error': 'No audio file provided'}), 400

        audio_file = request.files['audio']
        
        # Save audio file temporarily
        temp_dir = tempfile.mkdtemp()
        temp_path = os.path.join(temp_dir, audio_file.filename)
        audio_file.save(temp_path)

        # Transcribe audio with word-level timestamps
        result = model.transcribe(
            temp_path,
            word_timestamps=True,
            language="en"  # Adjust based on your needs
        )

        # Format word-level transcription with timestamps
        word_level_transcription = []
        for segment in result['segments']:
            for word in segment['words']:
                word_level_transcription.append({
                    'word': word['word'],
                    'start': word['start'],
                    'end': word['end'],
                    'confidence': word['probability']
                })

        # Clean up temporary file
        os.remove(temp_path)
        os.rmdir(temp_dir)

        # Return transcription results
        return jsonify({
            'transcription': word_level_transcription,
            'full_text': result['text']
        }), 200

    except Exception as e:
        return jsonify({'error': str(e)}), 500

if __name__ == '__main__':
    app.run(debug=True, host='0.0.0.0', port=7860)