Update app.py

app.py

@@ -3,8 +3,52 @@ from transformers import pipeline
 from transformers import AutoTokenizer, AutoModelForTokenClassification
 
 # Initialize the tokenizer and model
+import whisper
+import os
 
 app = Flask(__name__)
+
+
+
+# Load the model once at startup (better performance for multiple requests)
+model = whisper.load_model("small")
+
+def allowed_file(filename):
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in {'wav', 'mp3', 'ogg', 'flac', 'm4a'}
+
+@app.route('/transcribe', methods=['POST'])
+def transcribe_audio():
+    # Check if a file was uploaded
+    if 'file' not in request.files:
+        return jsonify({'error': 'No file uploaded'}), 400
+        
+    file = request.files['file']
+    
+    # Check if the file is empty
+    if file.filename == '':
+        return jsonify({'error': 'No selected file'}), 400
+        
+    # Check allowed file types
+    if not allowed_file(file.filename):
+        return jsonify({'error': 'Unsupported file type'}), 400
+
+    try:
+        # Save the temporary file
+        temp_path = "temp_audio"
+        file.save(temp_path)
+        
+        # Transcribe the audio
+        result = model.transcribe(temp_path)
+        transcription = result["text"]
+        
+        # Clean up the temporary file
+        if os.path.exists(temp_path):
+            os.remove(temp_path)
+            
+        return jsonify({'transcription': transcription})
+    
+    except Exception as e:
+        return jsonify({'error': str(e)}), 500
 classifier = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", return_all_scores=True)
 
 @app.route('/classify', methods=['POST'])