Update app.py

app.py

@@ -3,15 +3,13 @@ from huggingface_hub import InferenceClient
 import torch
 from TTS.api import TTS
 import soundfile as sf
-import os
-os.system("pip install fairseq==0.12.2")
 
-
-# Load TTS Model (supports multiple models)
+# Load TTS Model
 tts_model = TTS("tts_models/en/ljspeech/tacotron2-DDC").to("cuda" if torch.cuda.is_available() else "cpu")
 
-# Hugging Face LLM client
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# Hugging Face LLM client (DeepSeek R1 7B)
+client = InferenceClient("deepseek-ai/deepseek-r1-7b")
+
 
 def respond(
     message,
@@ -50,26 +48,24 @@ def respond(
     
     yield response, output_audio_path  # Yielding audio response
 
-# Gradio Chat Interface with Audio Output
-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)",
-        ),
-    ],
-    outputs=[
-        gr.Textbox(label="Generated Response"),
-        gr.Audio(type="filepath", label="TTS Output"),
-    ],
-)
 
-if __name__ == "__main__":
-    demo.launch()
+# Using gr.Blocks() instead of ChatInterface
+with gr.Blocks() as demo:
+    gr.Markdown("## DeepSeek R1 7B Chatbot with TTS")
+
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(label="User Input")
+    
+    system_msg = gr.Textbox(value="You are a friendly Chatbot.", label="System Message")
+    max_tokens = gr.Slider(1, 2048, value=512, step=1, label="Max Tokens")
+    temperature = gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature")
+    top_p = gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p (Nucleus Sampling)")
+    
+    tts_audio = gr.Audio(type="filepath", label="TTS Output")
+
+    def chat_fn(message, history):
+        return respond(message, history, system_msg.value, max_tokens.value, temperature.value, top_p.value)
+
+    msg.submit(chat_fn, inputs=[msg, chatbot], outputs=[chatbot, tts_audio])
+
+demo.launch()