Update app.py

app.py

@@ -4,6 +4,8 @@ from transformers import AutoTokenizer, AutoModelForTokenClassification
 import whisper
 import os
 
+import ffmpeg
+
 app = Flask(__name__)
 
 # Initialize Whisper model
@@ -17,9 +19,15 @@ 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
 
-def allowed_file(filename):
-    return '.' in filename and filename.rsplit('.', 1)[1].lower() in {'wav', 'mp3', 'ogg', 'flac', 'm4a'}
 
+def convert_audio(input_path, output_path):
+    try:
+        ffmpeg.input(input_path).output(output_path, acodec='pcm_s16le').run()
+        return True
+    except ffmpeg.Error as e:
+        print(f"FFmpeg error: {e.stderr.decode()}")
+        return False
+        
 @app.route('/transcribe', methods=['POST'])
 def transcribe_audio():
     if 'file' not in request.files:
@@ -37,18 +45,26 @@ def transcribe_audio():
         temp_path = "temp_audio"
         file.save(temp_path)
         
-        # Use the renamed whisper_model
-        result = whisper_model.transcribe(temp_path)
+        # Convert audio to a format Whisper can process
+        converted_path = "converted_audio.wav"
+        if not convert_audio(temp_path, converted_path):
+            return jsonify({'error': 'Audio conversion failed'}), 500
+        
+        # Transcribe the converted audio
+        result = whisper_model.transcribe(converted_path)
         transcription = result["text"]
         
+        # Clean up temporary files
         if os.path.exists(temp_path):
             os.remove(temp_path)
+        if os.path.exists(converted_path):
+            os.remove(converted_path)
             
         return jsonify({'transcription': transcription})
     
     except Exception as e:
         return jsonify({'error': str(e)}), 500
-
+        
 @app.route('/classify', methods=['POST'])
 def classify():
     try: