Files
media-to-text/server.py

70 lines
2.1 KiB
Python

#!/usr/bin/env python3
from flask import Flask, request, jsonify, send_from_directory
from flask_cors import CORS
import whisper
import os
import tempfile
app = Flask(__name__, static_folder=None)
CORS(app)
app.config['MAX_CONTENT_LENGTH'] = 50 * 1024 * 1024 # 50MB max (audio only)
@app.after_request
def set_headers(response):
response.headers['Cross-Origin-Opener-Policy'] = 'same-origin'
response.headers['Cross-Origin-Embedder-Policy'] = 'require-corp'
return response
print("Loading Whisper model...")
model = whisper.load_model("base")
print("Model loaded!")
ALLOWED_STATIC_FILES = {'index.html', 'app.js'}
@app.route('/')
def index():
return send_from_directory('.', 'index.html')
@app.route('/<path:filename>')
def static_files(filename):
if filename not in ALLOWED_STATIC_FILES:
return jsonify({'error': 'Not found'}), 404
return send_from_directory('.', filename)
@app.route('/transcribe', methods=['POST'])
def transcribe():
try:
if 'file' not in request.files:
return jsonify({'error': 'No file provided'}), 400
file = request.files['file']
language = request.form.get('language', None)
if language:
language = language.split('-')[0].lower()
if file.filename == '':
return jsonify({'error': 'No file selected'}), 400
# Enforce audio-only uploads (per DEVELOPMENT_RULES.md)
ext = os.path.splitext(file.filename)[1].lower()
video_exts = {'.mp4', '.avi', '.mov', '.mkv', '.flv', '.wmv', '.webm'}
if ext in video_exts:
return jsonify({'error': 'Video files not allowed. Extract audio first.'}), 400
with tempfile.NamedTemporaryFile(delete=False, suffix=os.path.splitext(file.filename)[1]) as tmp:
filepath = tmp.name
file.save(filepath)
try:
result = model.transcribe(filepath, language=language)
finally:
os.remove(filepath)
return jsonify({'text': result['text']})
except Exception as e:
return jsonify({'error': str(e)}), 500
if __name__ == '__main__':
app.run(debug=False, port=5000, host='127.0.0.1')