Update app.py (#5)

- Update app.py (75634697925a2f539634e0b6807b4d5ec1957e8b)


Co-authored-by: Sanchit Gandhi <[email protected]>

app.py

@@ -1,7 +1,9 @@
 import torch
+
 import gradio as gr
-from transformers import pipeline
 import pytube as pt
+from transformers import pipeline
+
 
 MODEL_NAME = "openai/whisper-small"
 
@@ -22,7 +24,6 @@ def transcribe(microphone, file_upload):
             "WARNING: You've uploaded an audio file and used the microphone. "
             "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
         )
-        file = microphone
 
     elif (microphone is None) and (file_upload is None):
         return "ERROR: You have to either use the microphone or upload an audio file"
@@ -37,15 +38,13 @@ def transcribe(microphone, file_upload):
 def _return_yt_html_embed(yt_url):
     video_id = yt_url.split("?v=")[-1]
     HTML_str = (
-        '<center><iframe width="500" height="320" src="https://www.youtube.com/embed/'
-        + video_id
-        + '"></iframe></center>'
+        f'<center> <iframe width="500" height="320" src="https://www.youtube.com/embed/{video_id}"> </iframe>'
+        " </center>"
     )
     return HTML_str
 
 
 def yt_transcribe(yt_url):
-
     yt = pt.YouTube(yt_url)
     html_embed_str = _return_yt_html_embed(yt_url)
     stream = yt.streams.filter(only_audio=True)[0]
@@ -67,29 +66,31 @@ mf_transcribe = gr.Interface(
     outputs="text",
     layout="horizontal",
     theme="huggingface",
-    title="Whisper Audio Transcribe",
-    description="Transcribe long audio/ microphone input (powered by 🤗transformers) with a click of a button!",
+    title="Whisper Demo: Transcribe Audio",
+    description=(
+        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the the fine-tuned"
+        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
+        " of arbitrary length."
+    ),
     allow_flagging="never",
 )
 
 yt_transcribe = gr.Interface(
     fn=yt_transcribe,
-    inputs=[
-        gr.inputs.Textbox(
-            lines=1, placeholder="Paste a URL to YT video here", label="yt_url"
-        )
-    ],
+    inputs=[gr.inputs.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL")],
     outputs=["html", "text"],
     layout="horizontal",
     theme="huggingface",
-    title="Whisper YT Transcribe",
-    description="Transcribe long YouTube videos (powered by 🤗transformers) with a click of a button!",
+    title="Whisper Demo: Transcribe YouTube",
+    description=(
+        "Transcribe long-form YouTube videos with the click of a button! Demo uses the the fine-tuned checkpoint:"
+        f" [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files of"
+        " arbitrary length."
+    ),
     allow_flagging="never",
 )
 
 with demo:
-    gr.TabbedInterface(
-        [mf_transcribe, yt_transcribe], ["Audio Transcribe", "YouTube Transcribe"]
-    )
+    gr.TabbedInterface([mf_transcribe, yt_transcribe], ["Transcribe Audio", "Transcribe YouTube"])
 
 demo.launch(enable_queue=True)