app.py

import gradio as gr

def to_audioClassification():
    return {
      audio_classification: gr.Row(visible=True),
      realtime_classification: gr.Row(visible=False),
      speech_recognition: gr.Row(visible=False),
      chatbot_qa: gr.Row(visible=False),
    }
    
def to_realtimeAudioClassification():
    return {
      audio_classification: gr.Row(visible=False),
      realtime_classification: gr.Row(visible=True),
      speech_recognition: gr.Row(visible=False),
      chatbot_qa: gr.Row(visible=False),
    }

def to_speechRecognition():
    return {
      audio_classification: gr.Row(visible=False),
      realtime_classification: gr.Row(visible=False),
      speech_recognition: gr.Row(visible=True),
      chatbot_qa: gr.Row(visible=False),
    }

def to_chatbot():
    return {
      audio_classification: gr.Row(visible=False),
      realtime_classification: gr.Row(visible=False),
      speech_recognition: gr.Row(visible=False),
      chatbot_qa: gr.Row(visible=True),
    }


with gr.Blocks() as demo:

    with gr.Accordion("Settings", open=True):
      language = gr.Radio(["en-us", "pt-br"], label="Language", info="Choose the language to display the classification result and audio", value='en-us', interactive=True)

    with gr.Row():
      btn0 = gr.Button("Audio Classification", scale=1,  size='lg')
      btn1 = gr.Button("Realtime Audio Classification", scale=1,size='lg')
      btn2 = gr.Button("Speech Recognition", scale=1, size='lg')
      btn3 = gr.Button("Help", scale=1, size='lg')

    with gr.Row(visible=False) as audio_classification:
          with gr.Column(min_width=700):
                with gr.Accordion("Record an Audio", open=True):
                  inputRecord = gr.Audio(label="Audio Input", source="microphone", type="filepath")
                with gr.Accordion("Upload a file", open=False):
                  inputUpload = gr.Audio(label="Audio Input", source="upload", type="filepath")
                clearBtn = gr.ClearButton([inputRecord, inputUpload])
          with gr.Column(min_width=700):
                output = gr.Label(label="Audio Classification")
                btn = gr.Button(value="Generate Audio")
                audioOutput = gr.Audio(label="Audio Output", interactive=False)


    with gr.Row(visible=False) as realtime_classification:
          with gr.Column(min_width=700):
                input = gr.Audio(label="Audio Input", source="microphone", type="filepath",streaming=True, every=10)
                historyOutput = gr.Textbox(label="History", interactive=False)
                # historyOutput = gr.Label(label="History")
          with gr.Column(min_width=700):
                output = gr.Label(label="Audio Classification")

    with gr.Row(visible=False) as speech_recognition:
          with gr.Column(min_width=700):
                with gr.Accordion("Record an Audio", open=True):
                  inputRecord = gr.Audio(label="Audio Input", source="microphone", type="filepath")
                with gr.Accordion("Upload a file", open=False):
                  inputUpload = gr.Audio(label="Audio Input", source="upload", type="filepath")
                clearBtn = gr.ClearButton([inputRecord])
          with gr.Column(min_width=700):
                output = gr.Label(label="Transcription")

    
    with gr.Row(visible=False) as chatbot_qa:
      chatbot = gr.Chatbot(
        [],
        elem_id="chatbot",
        bubble_full_width=False,
        # avatar_images=(None, "/content/avatar-socialear.png"),
        min_width=2000
      )
      with gr.Row(min_width=2000):
        txt = gr.Textbox(
              scale=4,
              show_label=False,
              placeholder="Enter text and press enter",
              container=False,
              min_width=1000
          )
        submit = gr.Button(value="", size='sm', scale=1)


    btn0.click(fn=to_audioClassification, outputs=[audio_classification, realtime_classification, speech_recognition, chatbot_qa])
    btn1.click(fn=to_realtimeAudioClassification, outputs=[audio_classification, realtime_classification, speech_recognition, chatbot_qa])
    btn2.click(fn=to_speechRecognition, outputs=[audio_classification, realtime_classification, speech_recognition, chatbot_qa])
    btn3.click(fn=to_chatbot, outputs=[audio_classification, realtime_classification, speech_recognition, chatbot_qa])


if __name__ == "__main__":
    demo.queue()
    demo.launch()