Create app.py

app.py

@@ -5,14 +5,19 @@ from transformers import pipeline
 import speech_recognition as sr
 from gtts import gTTS
 from io import BytesIO
+from pydub import AudioSegment
+import tempfile
 
-# Set your Hugging Face API key
+# Set Hugging Face API key (replace 'your_hugging_face_api_key' with your actual API key)
 os.environ["HUGGINGFACEHUB_API_TOKEN"] = "doctor app"
 
-# Load the Hugging Face model using text-generation
-chatbot = pipeline("text-generation", model="thrishala/mental_health_chatbot")
+# Load the Hugging Face model for text generation
+try:
+    chatbot = pipeline("text-generation", model="thrishala/mental_health_chatbot")
+except Exception as e:
+    st.error(f"Error loading model: {e}")
 
-# Function to get voice input using Whisper
+# Function to capture voice input using SpeechRecognition and OpenAI Whisper
 def get_voice_input():
     recognizer = sr.Recognizer()
     with sr.Microphone() as source:
@@ -20,7 +25,8 @@ def get_voice_input():
         audio = recognizer.listen(source)
         st.write("Recognizing...")
         try:
-            text = recognizer.recognize_whisper(audio)
+            # Converting audio to text using OpenAI Whisper if available, fallback to Google's API otherwise
+            text = recognizer.recognize_google(audio)
             return text
         except sr.UnknownValueError:
             st.error("Sorry, I could not understand the audio.")
@@ -31,11 +37,15 @@ def get_voice_input():
 
 # Function to generate voice response using gTTS
 def speak(text):
-    tts = gTTS(text=text, lang='en')
-    audio_file = BytesIO()
-    tts.save(audio_file)
-    audio_file.seek(0)
-    return audio_file
+    try:
+        tts = gTTS(text=text, lang='en')
+        audio_file = BytesIO()
+        tts.write_to_fp(audio_file)
+        audio_file.seek(0)
+        return audio_file
+    except Exception as e:
+        st.error(f"Error generating audio response: {e}")
+        return None
 
 # Streamlit app layout
 st.title("Mental Health Chatbot")
@@ -47,11 +57,15 @@ if st.button("Speak"):
     if user_input:
         st.write(f"You: {user_input}")
         # Get response from the chatbot
-        response = chatbot(user_input, max_length=150, num_return_sequences=1)[0]['generated_text']
-        st.write(f"Bot: {response}")
-        # Generate voice response
-        audio_output = speak(response)
-        st.audio(audio_output, format="audio/mp3")
+        try:
+            response = chatbot(user_input, max_length=150, num_return_sequences=1)[0]['generated_text']
+            st.write(f"Bot: {response}")
+            # Generate voice response
+            audio_output = speak(response)
+            if audio_output:
+                st.audio(audio_output, format="audio/mp3")
+        except Exception as e:
+            st.error(f"Error generating response: {e}")
 
 # Text input
 user_input = st.text_input("Type your message:")
@@ -59,8 +73,12 @@ if st.button("Send"):
     if user_input:
         st.write(f"You: {user_input}")
         # Get response from the chatbot
-        response = chatbot(user_input, max_length=150, num_return_sequences=1)[0]['generated_text']
-        st.write(f"Bot: {response}")
-        # Generate voice response
-        audio_output = speak(response)
-        st.audio(audio_output, format="audio/mp3")
+        try:
+            response = chatbot(user_input, max_length=150, num_return_sequences=1)[0]['generated_text']
+            st.write(f"Bot: {response}")
+            # Generate voice response
+            audio_output = speak(response)
+            if audio_output:
+                st.audio(audio_output, format="audio/mp3")
+        except Exception as e:
+            st.error(f"Error generating response: {e}")