Update app.py

app.py

@@ -1,5 +1,7 @@
 import gradio as gr
+import speech_recognition as sr
 from huggingface_hub import InferenceClient
+from io import BytesIO
 
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
@@ -11,29 +13,44 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    try:
+        messages = [{"role": "system", "content": system_message}]
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+        for val in history:
+            if val[0]:
+                messages.append({"role": "user", "content": val[0]})
+            if val[1]:
+                messages.append({"role": "assistant", "content": val[1]})
 
-    messages.append({"role": "user", "content": message})
+        messages.append({"role": "user", "content": message})
 
-    response = ""
+        response = ""
 
-    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
+        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
+            response += token
+            yield response
+    
+    except Exception as e:
+        yield f"An error occurred: {str(e)}"
 
-        response += token
-        yield response
+def recognize_speech(audio_file):
+    recognizer = sr.Recognizer()
+    with sr.AudioFile(audio_file) as source:
+        audio_data = recognizer.record(source)
+        try:
+            text = recognizer.recognize_google(audio_data)
+            return text
+        except sr.UnknownValueError:
+            return "Sorry, I could not understand the audio."
+        except sr.RequestError as e:
+            return f"Could not request results; {e}"
 
 # Define custom CSS
 custom_css = """
@@ -70,22 +87,23 @@ body {
 """
 
 # Create a Gradio chat interface with custom CSS
-demo = gr.ChatInterface(
-    fn=respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a Chatbot.Your name is Evy.Your are Developed By Joe.", 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)",
-        ),
-    ],
-    css=custom_css
-)
+with gr.Blocks(css=custom_css) as demo:
+    system_msg = gr.Textbox(value="You are a Chatbot. Your name is Evy. You are Developed By Joe.", label="System message")
+    max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new 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 (nucleus sampling)")
+    
+    input_textbox = gr.Textbox(label="Your message")
+    voice_input = gr.Audio(source="microphone", type="file", label="Record your message")
+    with gr.Row():
+        submit_button = gr.Button("Send")
+        voice_button = gr.Button("🎤 Speak")
+        
+    chatbot_output = gr.Textbox(label="Chatbot response", interactive=False)
 
+    submit_button.click(respond, inputs=[input_textbox, gr.State([]), system_msg, max_tokens, temperature, top_p], outputs=chatbot_output)
+    voice_input.change(lambda x: recognize_speech(BytesIO(x)), inputs=[voice_input], outputs=input_textbox)
+    
+# Launch the interface
 if __name__ == "__main__":
     demo.launch()