it is my first commit

app.py

@@ -1,64 +1,37 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 import gradio as gr
-from huggingface_hub import InferenceClient
+from gtts import gTTS
+from langdetect import detect
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
 
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float32)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+def respond(user_input):
+    if not user_input:
+        return "Please ask something.", None
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    detected_lang = detect(user_input)
 
-    messages.append({"role": "user", "content": message})
+    prompt = f"[INST] {user_input} [/INST]"
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=256, pad_token_id=tokenizer.eos_token_id)
 
-    response = ""
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    # Voice output
+    tts = gTTS(text=response, lang='hi' if detected_lang == 'hi' else 'en')
+    tts.save("voice_response.mp3")
+    return response, "voice_response.mp3"
 
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+iface = gr.Interface(
+    fn=respond,
+    inputs=gr.Textbox(lines=2, placeholder="Ask me anything..."),
+    outputs=[gr.Textbox(label="TeachMe Says"), gr.Audio(label="Voice", autoplay=True)],
+    title="TeachMe - Your Smart Tutor",
+    description="Light AI bot with Hindi + English voice support."
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+iface.launch()