Update app.py

app.py

@@ -1,17 +1,17 @@
+import torch
+
 import gradio as gr
 import yt_dlp as youtube_dl
 from transformers import pipeline
 from transformers.pipelines.audio_utils import ffmpeg_read
-import torch
 
 import tempfile
 import os
-import time
 
 MODEL_NAME = "openai/whisper-large-v3"
 BATCH_SIZE = 8
 FILE_LIMIT_MB = 1000
-YT_LENGTH_LIMIT_S = 3600
+YT_LENGTH_LIMIT_S = 3600  # limit to 1 hour YouTube files
 
 device = 0 if torch.cuda.is_available() else "cpu"
 
@@ -22,12 +22,14 @@ 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]
@@ -68,6 +70,7 @@ 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)
 
@@ -84,10 +87,8 @@ def yt_transcribe(yt_url, task, max_filesize=75.0):
 
     return html_embed_str, text
 
-demo = gr.Blocks(theme="TogetherAi/Alex2")
 
-demo.layout = "centered"
-demo.width = 500
+demo = gr.Blocks()
 
 mf_transcribe = gr.Interface(
     fn=transcribe,
@@ -96,21 +97,17 @@ mf_transcribe = gr.Interface(
         gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
     ],
     outputs="text",
-    layout="vertical",  # Ändere das Layout auf "vertical"
-    theme="TogetherAi/Alex2",
-    title="Whisper Large V3: Audio transkribieren",
+    layout="horizontal",
+    theme="TogetherAI/Alex2 ",
+    title="Whisper Large V3: Transcribe Audio",
     description=(
-        "Transkribiere lange Mikrofon- oder Audioeingaben mit einem Klick! Die Demo verwendet den"
-        f" Checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) und 🤗 Transformers, um Audiodateien"
-        " beliebiger Länge zu transkribieren."
+        "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",
 )
 
-# Ändere das Layout für den Button auf "centered" und setze die Breite des Buttons auf 200 Pixel
-mf_transcribe[0].style['justify-content'] = 'center'
-mf_transcribe[1].style['width'] = '200px'
-
 file_transcribe = gr.Interface(
     fn=transcribe,
     inputs=[
@@ -118,21 +115,17 @@ file_transcribe = gr.Interface(
         gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
     ],
     outputs="text",
-    layout="vertical",  # Ändere das Layout auf "vertical"
-    theme="TogetherAi/Alex2",
+    layout="horizontal",
+    theme="TogetherAI/Alex2",
     title="Whisper Large V3: Transcribe Audio",
     description=(
-        "Transkribiere lange Mikrofon- oder Audioeingaben mit einem Klick! Die Demo verwendet den"
-        f" Checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) und 🤗 Transformers, um Audiodateien"
-        " beliebiger Länge zu transkribieren."
+        "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",
 )
 
-# Ändere das Layout für den Button auf "centered" und setze die Breite des Buttons auf 200 Pixel
-file_transcribe[0].style['justify-content'] = 'center'
-file_transcribe[1].style['width'] = '200px'
-
 yt_transcribe = gr.Interface(
     fn=yt_transcribe,
     inputs=[
@@ -140,22 +133,18 @@ yt_transcribe = gr.Interface(
         gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe")
     ],
     outputs=["html", "text"],
-    layout="vertical",  # Ändere das Layout auf "vertical"
-    theme="TogetherAi/Alex2",
+    layout="horizontal",
+    theme="TogetherAI/Alex2",
     title="Whisper Large V3: Transcribe YouTube",
     description=(
-        "Transkribiere lange Mikrofon- oder Audioeingaben mit einem Klick! Die Demo verwendet den"
-        f" Checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) und 🤗 Transformers, um Audiodateien"
-        " beliebiger Länge zu transkribieren."
+        "Transcribe long-form YouTube videos with the click of a button! Demo uses the checkpoint"
+        f" [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe video files of"
+        " arbitrary length."
     ),
     allow_flagging="never",
 )
 
-# Ändere das Layout für den Button auf "centered" und setze die Breite des Buttons auf 200 Pixel
-yt_transcribe[0].style['justify-content'] = 'center'
-yt_transcribe[1].style['width'] = '200px'
-
 with demo:
     gr.TabbedInterface([mf_transcribe, file_transcribe, yt_transcribe], ["Microphone", "Audio file", "YouTube"])
 
-demo.launch(enable_queue=True)
+demo.launch(enable_queue=True)