Update app.py

app.py

@@ -1,14 +1,14 @@
 import torch
-from transformers import Wav2Vec2Tokenizer, Wav2Vec2ForCTC
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Tokenizer
 import sounddevice as sd
 import soundfile as sf
 import numpy as np
 import requests
 import webbrowser
-from sklearn.preprocessing import LabelEncoder
+import os
 
-# Load pre-trained model and tokenizer
-model_name = "facebook/wav2vec2-large-xlsr-53"  # Change to the specific model you need for emotion recognition
+# Load pre-trained Wav2Vec2 model and tokenizer
+model_name = "facebook/wav2vec2-large-xlsr-53"  # Model name for audio processing
 tokenizer = Wav2Vec2Tokenizer.from_pretrained(model_name)
 model = Wav2Vec2ForCTC.from_pretrained(model_name)
 
@@ -20,16 +20,12 @@ def record_audio(duration=5, fs=16000):
     print("Recording finished.")
     return audio.flatten()
 
-# Function to save audio file
-def save_audio(filename, audio, fs=16000):
-    sf.write(filename, audio, fs)
-
 # Function for emotion recognition
 def recognize_emotion(audio):
-    # Convert audio array to input suitable for the model
+    # Normalize audio if necessary (check your audio data properties if required)
     input_values = tokenizer(audio, return_tensors='pt', padding='longest', sampling_rate=16000).input_values
 
-    # Store logits (raw predictions) and apply softmax to get probabilities
+    # Get the logits (raw predictions) and apply softmax to get probabilities
     with torch.no_grad():
         logits = model(input_values).logits
         predicted_ids = torch.argmax(logits, dim=-1)
@@ -39,44 +35,41 @@ def recognize_emotion(audio):
 
     return transcription  # Return the detected text
 
-# Function to map emotion text to playlist (customizable)
+# Function to get Spotify playlist based on mood
 def get_playlist(mood):
     url = "https://unsa-unofficial-spotify-api.p.rapidapi.com/search"
-    querystring = {"query": mood, "count":"10", "type": "playlists"}
+    querystring = {"query": mood, "count": "10", "type": "playlists"}
     headers = {
         'x-rapidapi-key': "your-api-key",  # Replace with your actual API key
         'x-rapidapi-host': "unsa-unofficial-spotify-api.p.rapidapi.com"
     }
 
-    response = requests.get(url, headers=headers, params=querystring)
-    playlist_id = response.json()["Results"][0]["id"]  # Choose the first playlist
-
-    return playlist_id
-
-# Function to open playlist URL
+    try:
+        response = requests.get(url, headers=headers, params=querystring)
+        response.raise_for_status()  # Raises error for bad responses
+        playlist_id = response.json()["Results"][0]["id"]  # Get the first playlist
+        return playlist_id
+    except requests.exceptions.RequestException as e:
+        print(f"Error fetching playlist data: {e}")
+        return None
+
+# Function to open the Spotify playlist in a web browser
 def open_playlist(playlist_id):
     webbrowser.open(f'https://open.spotify.com/playlist/{playlist_id}')
 
-# Main function to run the recorder and emotion recognizer
+# Main function to record audio and recognize mood
 def main():
-    try:
-        # Record audio
-        audio = record_audio()
-
-        # Save audio to file
-        filename = "output.wav"
-        save_audio(filename, audio)
+    # Record audio
+    audio = record_audio()
 
-        # Recognize the mood/emotion from audio
-        emotion_text = recognize_emotion(audio)
-        print(f"Detected Emotion: {emotion_text}")
+    # Recognize the mood/emotion from audio
+    emotion_text = recognize_emotion(audio)
+    print(f"Detected Emotion: {emotion_text}")
 
-        # Get playlist based on detected emotion
-        playlist_id = get_playlist(emotion_text)
+    # Get Spotify playlist based on the detected emotion
+    playlist_id = get_playlist(emotion_text)
+    if playlist_id:
         open_playlist(playlist_id)
 
-    except Exception as e:
-        print(f"An error occurred: {e}")
-
 if __name__ == "__main__":
     main()