update

app.py

@@ -1,20 +1,22 @@
 import os
 import streamlit as st
 import requests
-from gtts import gTTS
 from transformers import pipeline
 from PIL import Image
 from dotenv import load_dotenv
 
-API_URL = "https://api-inference.huggingface.co/models/trpakov/vit-face-expression"
-headers = {"Authorization": f"Bearer {os.getenv('HUGGINGFACE_API_KEY')}"}
+# Load environment variables from .env file
+load_dotenv()
 
-# Your existing functions and Streamlit code...
+# Set up the Hugging Face API URL and your API key
+headers = {"Authorization": f"Bearer {os.getenv('HUGGINGFACE_API_KEY')}"}
 
-# Example query function
+# Function to query the Hugging Face model for facial expression
 def query(filename):
     with open(filename, "rb") as f:
         data = f.read()
+    # Use the facial expression model
+    API_URL = "https://api-inference.huggingface.co/models/microsoft/face-expression-recognition"
     response = requests.post(API_URL, headers=headers, data=data)
     
     if response.status_code == 200:
@@ -25,16 +27,15 @@ def query(filename):
 
 # Function to generate a joke or uplifting text based on the mood
 def generate_text_based_on_mood(emotion):
-    generator = pipeline('text-generation', model='gpt2')
-    prompt = f"Tell a joke that would cheer someone who is feeling {emotion}."
-    response = generator(prompt, max_length=50, num_return_sequences=1)
-    return response[0]['generated_text']
-
-# Function to convert text to speech using gTTS
-def text_to_speech(text):
-    tts = gTTS(text, lang='en')
-    tts.save("output.mp3")  # Save to a file
-    return "output.mp3"  # Return the filename for playing
+    try:
+        # Use GPT-Neo model
+        generator = pipeline('text-generation', model='EleutherAI/gpt-neo-125M')
+        prompt = f"Tell a joke that would cheer someone who is feeling {emotion}."
+        response = generator(prompt, max_length=50, num_return_sequences=1)
+        return response[0]['generated_text']
+    except Exception as e:
+        st.error(f"Error generating text: {e}")
+        return "Sorry, I couldn't come up with a joke at this moment."
 
 # Streamlit UI
 st.title("Facial Expression Mood Detector")
@@ -55,16 +56,10 @@ if uploaded_file is not None:
     # Detect facial expression
     expression_output = query("uploaded_image.jpg")
     if expression_output:
-        emotion = expression_output[0]['label']  # Adjust as per the actual response structure
+        emotion = expression_output[0]['label']  # Adjust based on response structure
         st.write(f"Detected emotion: {emotion}")
 
         # Generate text based on detected emotion
         joke = generate_text_based_on_mood(emotion)
         st.write("Here's something to cheer you up:")
         st.write(joke)
-
-        # Convert the generated joke to audio
-        audio_file = text_to_speech(joke)
-
-        # Provide an audio player in the Streamlit app
-        st.audio(audio_file)  # Streamlit will handle playback