Update app.py

app.py

@@ -1,5 +1,4 @@
 import torch
-
 import gradio as gr
 import yt_dlp as youtube_dl
 from transformers import pipeline
@@ -7,6 +6,7 @@ from transformers.pipelines.audio_utils import ffmpeg_read
 
 import tempfile
 import os
+import time
 
 MODEL_NAME = "openai/whisper-large-v3"
 BATCH_SIZE = 8
@@ -22,14 +22,12 @@ pipe = pipeline(
     device=device,
 )
 
-
 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 = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
-    return  text
-
+    return text
 
 def _return_yt_html_embed(yt_url):
     video_id = yt_url.split("?v=")[-1]
@@ -70,7 +68,6 @@ def download_yt_audio(yt_url, filename):
         except youtube_dl.utils.ExtractorError as err:
             raise gr.Error(str(err))
 
-
 def yt_transcribe(yt_url, task, max_filesize=75.0):
     html_embed_str = _return_yt_html_embed(yt_url)
 
@@ -87,14 +84,11 @@ def yt_transcribe(yt_url, task, max_filesize=75.0):
 
     return html_embed_str, text
 
-
-demo = gr.Blocks()
-
 mf_transcribe = gr.Interface(
     fn=transcribe,
     inputs=[
-        gr.inputs.Audio(source="microphone", type="filepath", optional=True),
-        gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
+        gr.Audio(source="microphone", type="filepath", optional=True),
+        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
     ],
     outputs="text",
     layout="horizontal",
@@ -111,8 +105,8 @@ mf_transcribe = gr.Interface(
 file_transcribe = gr.Interface(
     fn=transcribe,
     inputs=[
-        gr.inputs.Audio(source="upload", type="filepath", optional=True, label="Audio file"),
-        gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
+        gr.Audio(source="upload", type="filepath", optional=True, label="Audio file"),
+        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
     ],
     outputs="text",
     layout="horizontal",
@@ -129,8 +123,8 @@ file_transcribe = gr.Interface(
 yt_transcribe = gr.Interface(
     fn=yt_transcribe,
     inputs=[
-        gr.inputs.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL"),
-        gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe")
+        gr.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL"),
+        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe")
     ],
     outputs=["html", "text"],
     layout="horizontal",
@@ -144,8 +138,7 @@ yt_transcribe = gr.Interface(
     allow_flagging="never",
 )
 
-with demo:
+with gr.Blocks() as demo:
     gr.TabbedInterface([mf_transcribe, file_transcribe, yt_transcribe], ["Microphone", "Audio file", "YouTube"])
 
 demo.launch(enable_queue=True)
-