from flask import Flask, request, jsonify from transformers import pipeline from transformers import AutoTokenizer, AutoModelForTokenClassification import whisper import os import ffmpeg app = Flask(__name__) # Initialize Whisper model whisper_model = whisper.load_model("small") # Renamed variable # Initialize Emotion Classifier classifier = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base", return_all_scores=True) # Initialize NER pipeline ner_tokenizer = AutoTokenizer.from_pretrained("dslim/bert-base-NER") ner_model = AutoModelForTokenClassification.from_pretrained("dslim/bert-base-NER") # Renamed variable ner_pipeline = pipeline("ner", model=ner_model, tokenizer=ner_tokenizer) # Renamed variable @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 try: # Save the uploaded file to a temporary file with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as temp_audio: file.save(temp_audio) temp_path = temp_audio.name # Transcribe the audio using Whisper result = whisper_model.transcribe(temp_path) transcription = result["text"] # Clean up the temporary file os.remove(temp_path) return jsonify({'transcription': transcription}) except Exception as e: return jsonify({'error': str(e)}), 500 @app.route('/classify', methods=['POST']) def classify(): try: data = request.get_json() if 'text' not in data: return jsonify({"error": "Missing 'text' field"}), 400 text = data['text'] result = classifier(text) return jsonify(result) except Exception as e: return jsonify({"error": str(e)}), 500 @app.route('/ner', methods=['POST']) def ner_endpoint(): try: data = request.get_json() text = data.get("text", "") # Use the renamed ner_pipeline ner_results = ner_pipeline(text) words_and_entities = [ {"word": result['word'], "entity": result['entity']} for result in ner_results ] return jsonify({"entities": words_and_entities}) except Exception as e: return jsonify({"error": str(e)}), 500