Update app.py

app.py

@@ -5,7 +5,7 @@ import whisper
 import os
 import tempfile
 import io
-
+import torchaudio
 
 app = Flask(__name__)
 
@@ -24,24 +24,29 @@ ner_pipeline = pipeline("ner", model=ner_model, tokenizer=ner_tokenizer)  # Rena
 @app.route('/transcribe', methods=['POST'])
 def transcribe():
     try:
-        # Read the raw audio bytes
-        audio_bytes = request.data  # Get raw bytes from request
+        # Read raw bytes from the request
+        audio_bytes = request.data  
         if not audio_bytes:
             return jsonify({"error": "No audio data provided"}), 400
 
         # Convert bytes to a file-like object
         audio_file = io.BytesIO(audio_bytes)
 
+        # Load audio as a waveform using torchaudio
+        waveform, sample_rate = torchaudio.load(audio_file)
+
+        # Whisper expects a NumPy array, so we convert it
+        audio_numpy = waveform.squeeze().numpy()
+
         # Transcribe the audio
-        result = whisper_model.transcribe(audio_file)
+        result = model.transcribe(audio_numpy)
 
         return jsonify({"text": result["text"]})
 
     except Exception as e:
-        print("Error:", str(e))  # Log the error
+        print("Error:", str(e))  # Log error for debugging
         return jsonify({"error": "Internal Server Error", "details": str(e)}), 500
 
-
         
         
 @app.route('/classify', methods=['POST'])