update

app.py

@@ -1,6 +1,6 @@
 import os
-import streamlit as st
 import requests
+import streamlit as st
 from transformers import pipeline
 from PIL import Image
 from dotenv import load_dotenv
@@ -9,14 +9,13 @@ from dotenv import load_dotenv
 load_dotenv()
 
 # Set up the Hugging Face API URL and your API key
+API_URL = "https://api-inference.huggingface.co/models/trpakov/vit-face-expression"
 headers = {"Authorization": f"Bearer {os.getenv('HUGGINGFACE_API_KEY')}"}
 
 # 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:
@@ -28,7 +27,7 @@ def query(filename):
 # Function to generate a joke or uplifting text based on the mood
 def generate_text_based_on_mood(emotion):
     try:
-        # Use GPT-Neo model
+        # Use GPT-Neo model for text generation
         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)
@@ -37,6 +36,14 @@ def generate_text_based_on_mood(emotion):
         st.error(f"Error generating text: {e}")
         return "Sorry, I couldn't come up with a joke at this moment."
 
+# Function to convert text to speech using gTTS
+def text_to_speech(text):
+    from gtts import gTTS
+    tts = gTTS(text, lang='en')
+    audio_file = "output.mp3"
+    tts.save(audio_file)  # Save the audio file
+    return audio_file
+
 # Streamlit UI
 st.title("Facial Expression Mood Detector")
 st.write("Upload an image of a face to detect mood and receive uplifting messages or jokes.")
@@ -56,6 +63,7 @@ if uploaded_file is not None:
     # Detect facial expression
     expression_output = query("uploaded_image.jpg")
     if expression_output:
+        # Assuming the response has a 'label' field with the detected emotion
         emotion = expression_output[0]['label']  # Adjust based on response structure
         st.write(f"Detected emotion: {emotion}")
 
@@ -63,3 +71,9 @@ if uploaded_file is not None:
         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