update

README.md

@@ -1,73 +1,44 @@
----
-license: mit
----
-Here’s the revised README for the **Mood Parser** project on Hugging Face, using the correct repo name `RummyAx/Mood-Parser`:
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from gtts import gTTS
+import os
+
+# Load Mistral 7B Chat Model
+model_name = "mistralai/Mistral-7B-Instruct"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Function to generate AI response
+def chatbot_response(user_input):
+    inputs = tokenizer(user_input, return_tensors="pt")
+    outputs = model.generate(**inputs, max_length=200)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+# Function to convert AI response to speech
+def text_to_speech(text):
+    tts = gTTS(text=text, lang="en")
+    filename = "response.mp3"
+    tts.save(filename)
+    return filename
+
+# Gradio Interface
+def chat_interface(user_input):
+    ai_response = chatbot_response(user_input)
+    audio_file = text_to_speech(ai_response)
+    return ai_response, audio_file
+
+# Launch Gradio UI
+demo = gr.Interface(
+    fn=chat_interface,
+    inputs=gr.Textbox(label="Ask ZEAL.AI"),
+    outputs=[gr.Textbox(label="AI Response"), gr.Audio(label="Text-to-Speech Output")],
+    title="ZEAL.AI - Bible AI Chatbot",
+    description="Ask anything and get a spoken response!"
+)
+
+demo.launch()
 
-```markdown
-# Mood Parser AI: Moodly
-
-**Moodly** is an AI-powered Mood Parser that detects emotions in text using a fine-tuned transformer-based model, such as BERT or RoBERTa. Deployed on Hugging Face, it offers real-time mood analysis and emotion classification across multiple languages.
-
-## Demo
-
-You can try **Moodly** directly on Hugging Face:
-
-[Try Moodly](https://huggingface.co/spaces/RummyAx/Mood-Parser)
-
-## How it Works
-
-Moodly detects a variety of emotions from text input. The model is trained on sentiment and emotion classification tasks to provide accurate results. It supports multiple languages for global usage.
-
-### Supported Emotions
-
-- Happiness
-- Sadness
-- Anger
-- Fear
-- Surprise
-- Disgust
-
-## Example
-
-### Input:
-```text
-I am feeling really happy today!
-```
-
-### Output:
-```json
-{
-  "emotion": "happiness",
-  "confidence": 0.97
-}
-```
-
-## API Usage
-
-You can integrate the model into your applications using Hugging Face's API.
-
-### API Endpoint
-
-- **URL**: `https://api-inference.huggingface.co/models/RummyAx/Mood-Parser`
-- **Method**: POST
-- **Body**: Send a POST request with the input text.
-
-### Example API Request:
-
-```bash
-curl -X POST "https://api-inference.huggingface.co/models/RummyAx/Mood-Parser" \
-  -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" \
-  -H "Content-Type: application/json" \
-  -d '{"inputs": "I am feeling very sad!"}'
-```
-
-### Example API Response:
-
-```json
-{
-  "emotion": "sadness",
-  "confidence": 0.95
-}
 ```
 
 ## Installation (Local)