Update app.py

app.py

@@ -1,25 +1,40 @@
 import gradio as gr
-import requests
-from io import BytesIO
-from pydub import AudioSegment
-
-def translate_audio_to_audio(audio):
-    # Send the audio data to the translation model
-    translation_response = requests.post(
-        "https://api-inference.huggingface.co/models/facebook/xm_transformer_s2ut_hk-en",
-        files={"file": audio},
-    )
-
-    # Get the translated audio from the response
-    translated_audio_bytes = translation_response.content
-    translated_audio = AudioSegment.from_file(BytesIO(translated_audio_bytes))
-
-    return translated_audio
-
-gr.Interface(
-    fn=translate_audio_to_audio,
-    inputs=gr.Audio(source="microphone", type="file", label="Speak something"),
-    outputs=gr.Audio(type="file", label="Translated Audio"),
-    live=True
-).launch()
 
+
+def click_js():
+    return """function audioRecord() {
+    var xPathRes = document.evaluate ('//*[@id="audio"]//button', document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null); 
+    xPathRes.singleNodeValue.click();}"""
+
+
+def action(btn):
+    """Changes button text on click"""
+    if btn == 'Speak': return 'Stop'
+    else: return 'Speak'
+
+
+def check_btn(btn):
+    """Checks for correct button text before invoking transcribe()"""
+    if btn != 'Speak': raise Exception('Recording...')
+
+
+def transcribe():
+    return 'Success'
+
+
+with gr.Blocks() as demo:
+    msg = gr.Textbox()
+    audio_box = gr.Audio(label="Audio", source="microphone", type="filepath", elem_id='audio')
+
+    with gr.Row():
+        audio_btn = gr.Button('Speak')
+        clear = gr.Button("Clear")
+
+    audio_btn.click(fn=action, inputs=audio_btn, outputs=audio_btn).\
+              then(fn=lambda: None, _js=click_js()).\
+              then(fn=check_btn, inputs=audio_btn).\
+              success(fn=transcribe, outputs=msg)
+
+    clear.click(lambda: None, None, msg, queue=False)
+
+demo.queue().launch(debug=True)