Update app.py

app.py

@@ -1,63 +1,54 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    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]})
-
-    messages.append({"role": "user", "content": message})
-
-    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
-
-        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)",
-        ),
+from gtts import gTTS
+from io import BytesIO
+import IPython.display as ipd
+
+# Load CodeLlama model
+codellama_model = gr.Interface.load("models/meta-llama/CodeLlama-7b-Python-hf")
+
+# Load deepseek-coder model
+deepseek_model = gr.Interface.load("models/deepseek-ai/deepseek-coder-1.3b-instruct")
+
+# Define function to process text input for CodeLlama model
+def process_text_codellama(input_text):
+    return codellama_model.predict(input_text)
+
+# Define function to process speech input for CodeLlama model
+def process_speech_codellama(audio):
+    response = codellama_model.predict(audio)
+    tts = gTTS(text=response, lang='en')
+    fp = BytesIO()
+    tts.write_to_fp(fp)
+    fp.seek(0)
+    return ipd.Audio(fp.read(), autoplay=True)
+
+# Define function to process text input for deepseek model
+def process_text_deepseek(input_text):
+    return deepseek_model.predict(input_text)
+
+# Define function to process speech input for deepseek model
+def process_speech_deepseek(audio):
+    response = deepseek_model.predict(audio)
+    tts = gTTS(text=response, lang='en')
+    fp = BytesIO()
+    tts.write_to_fp(fp)
+    fp.seek(0)
+    return ipd.Audio(fp.read(), autoplay=True)
+
+# Add voice input and text input with responsive button
+inputs = [
+    gr.inputs.Textbox(label="Type your code", placeholder="Type your code here...", lines=10),
+    gr.inputs.Checkbox(label="Enable voice input", default=False),
+    "text" # Dropdown for model selection
+]
+
+# Launch interface with live=True
+gr.Interface(
+    fn=[
+        [process_text_codellama, process_speech_codellama],
+        [process_text_deepseek, process_speech_deepseek]
     ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+    inputs=inputs,
+    outputs=["text", "audio"],
+    live=True
+).launch()