Update app.py

app.py

@@ -74,40 +74,72 @@ def respond(
 @spaces.GPU
 def transcribe(inputs, task):
     if inputs is None:
-        raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
-
-    text = asr_pl(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
+        raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.") 
+        
+    text = asr_pl(asr_inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
     return  text
 
 demo = gr.Blocks()
-
-transcribe_interface
+audio_input = gr.Audio(sources="upload", type="filepath", label="Audio file")
+audio_input_choice = gr.Radio(["audio file", "microphone"], label="Audio", value="audio file")
+task_input_choice = gr.Radio(["transcribe", "translate"], label="Task", value="transcribe")
+
+transcribe_interface = gr.Interface(
+    fn=transcribe,
+    inputs=[
+        audio_input,
+        audio_input_choice,
+        task_input_choice,
+    ],
+    outputs="text",
+    title="Whisper Large V3: Transcribe Audio",
+    description=(
+        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the"
+        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
+        " of arbitrary length."
+    ),
+    allow_flagging="never",
+)
 
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
 
-chat_interface = gr.ChatInterface(
-    respond,
-    title="Enlight Innovations Limited -- Demo",
-    description="This demo is desgined to illustrate our basic idea and feasibility in implementation.",
-    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(
+application_title = "Enlight Innovations Limited -- Demo"
+application_description = "This demo is desgined to illustrate our basic idea and feasibility in implementation."
+chatbot_sys_output = gr.Textbox(value="You are a friendly Chatbot.", label="System message")
+chatbot_max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
+chatbot_temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
+chatbot_top_p = gr.Slider(
             minimum=0.1,
             maximum=1.0,
             value=0.95,
             step=0.05,
             label="Top-p (nucleus sampling)",
-        ),
+        )
+
+chat_interface = gr.ChatInterface(
+    respond,
+    title=application_title,
+    description=application_description,
+    additional_inputs=[
+        chatbot_sys_output,
+        chatbot_max_tokens,
+        chatbot_temperature,
+        chatbot_top_p,
     ],
 )
 
+def update_audio_input(audio_input_choice):
+    if user_choice == "audio file":
+        return gr.Audio(sources="upload", type="filepath", label="Audio file")
+    elif user_choice == "microphone":
+        gr.Audio(sources="microphone", type="filepath")
+
 with demo:
-    gr.TabbedInterface([transcribe_interface, chat_interface], ["Step 1: Transcribe", "Step 2: "])
+    gr.TabbedInterface([transcribe_interface, chat_interface], ["Step 1: Transcribe", "Step 2: Extract"])
+    audio_input_choice.change(update_audio_input, audio_input_choice, audio_input)
 
 if __name__ == "__main__":
     demo.queue().launch() #demo.launch()