Update app.py

app.py

@@ -2,39 +2,31 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 from transformers import pipeline
 
+# Load LLM
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-
+# Load Speech-to-Text (STT) model
 stt_pipeline = pipeline("automatic-speech-recognition", model="openai/whisper-base")
 
-
+# Load Text-to-Speech (TTS) model (using a public model without token requirements)
 tts_pipeline = pipeline("text-to-speech", model="facebook/mms-tts-eng")
 
-
-def respond(
-    audio,  # Audio input from microphone
-    message,  # Text input
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    # Convert speech to text if audio input is given
-    if audio:
+def respond(audio, message, history, system_message, max_tokens, temperature, top_p):
+    # Convert speech to text if audio input is provided
+    if audio is not None:
         message = stt_pipeline(audio)["text"]
 
-    # Prepare message history for LLM
+    # Prepare conversation history
     messages = [{"role": "system", "content": system_message}]
     for user_msg, bot_msg in history:
         if user_msg:
             messages.append({"role": "user", "content": user_msg})
         if bot_msg:
             messages.append({"role": "assistant", "content": bot_msg})
-
+    
     messages.append({"role": "user", "content": message})
 
-    # Get response from LLM
+    # Generate response from LLM
     response = ""
     for msg in client.chat_completion(
         messages, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p
@@ -42,27 +34,36 @@ def respond(
         token = msg.choices[0].delta.content
         response += token
 
-    # Convert chatbot's text response into speech
+    # Convert chatbot response to speech
     speech = tts_pipeline(response)
 
     return history + [(message, response)], speech["audio"]
 
-# Gradio Interface
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Audio(source="microphone", type="filepath", label="🎙️ Speak"),
-        gr.Textbox(label="💬 Or type your message"),
-        gr.Textbox(value="You are a friendly AI 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"),
-    ],
-    output_components=[
-        gr.Chatbot(label="Chat History"),
-        gr.Audio(label="🔊 AI Response"),
-    ],
-)
+# Gradio Interface using Blocks
+with gr.Blocks() as demo:
+    gr.Markdown("# 🎙️ Chatbot with Speech & Text")
+
+    with gr.Row():
+        audio_input = gr.Audio(type="filepath", label="🎤 Speak (or type below)")
+        text_input = gr.Textbox(label="💬 Or type your message")
+
+    chatbot = gr.Chatbot(label="Chat History")
+
+    with gr.Row():
+        system_msg = gr.Textbox(value="You are a friendly AI chatbot.", label="System Message")
+        max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max Tokens")
+        temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
+        top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p")
+
+    audio_output = gr.Audio(label="🔊 AI Response")
+
+    submit = gr.Button("Send")
+
+    submit.click(
+        respond,
+        inputs=[audio_input, text_input, chatbot, system_msg, max_tokens, temperature, top_p],
+        outputs=[chatbot, audio_output]
+    )
 
 if __name__ == "__main__":
     demo.launch()