Fix and add ZeroGPU support (#137)

- Update app.py (405f94bfcf7ba36d21847ee6d12faccc3c92dbbc)
- Update README.md (2d34652bdf66e74ae7b6b0a835208d3da7d25f5b)


Co-authored-by: Apolinário from multimodal AI art <multimodalart@users.noreply.huggingface.co>

README.md

@@ -4,9 +4,9 @@ emoji: 📉
 colorFrom: pink
 colorTo: yellow
 sdk: gradio
-sdk_version: 3.38.0
+sdk_version: 5.46.0
 app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,5 +1,6 @@
 import torch
 
+import spaces
 import gradio as gr
 import yt_dlp as youtube_dl
 from transformers import pipeline
@@ -22,7 +23,7 @@ pipe = pipeline(
     device=device,
 )
 
-
+@spaces.GPU
 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.")
@@ -70,7 +71,7 @@ def download_yt_audio(yt_url, filename):
         except youtube_dl.utils.ExtractorError as err:
             raise gr.Error(str(err))
 
-
+@spaces.GPU
 def yt_transcribe(yt_url, task, max_filesize=75.0):
     html_embed_str = _return_yt_html_embed(yt_url)
 
@@ -88,35 +89,13 @@ 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"),
-    ],
-    outputs="text",
-    layout="horizontal",
-    theme="huggingface",
-    title="Whisper Large V3: Transcribe Audio",
-    description=(
-        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the OpenAI Whisper"
-        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
-        " of arbitrary length."
-    ),
-    allow_flagging="never",
-)
-
-file_transcribe = gr.Interface(
+demo = 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(type="filepath"),
+        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
     ],
-    outputs="text",
-    layout="horizontal",
-    theme="huggingface",
+    outputs=gr.Textbox(lines=3),
     title="Whisper Large V3: Transcribe Audio",
     description=(
         "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the OpenAI Whisper"
@@ -126,26 +105,4 @@ file_transcribe = gr.Interface(
     allow_flagging="never",
 )
 
-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")
-    ],
-    outputs=["html", "text"],
-    layout="horizontal",
-    theme="huggingface",
-    title="Whisper Large V3: Transcribe YouTube",
-    description=(
-        "Transcribe long-form YouTube videos with the click of a button! Demo uses the OpenAI Whisper checkpoint"
-        f" [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe video files of"
-        " arbitrary length."
-    ),
-    allow_flagging="never",
-)
-
-with demo:
-    gr.TabbedInterface([mf_transcribe, file_transcribe, yt_transcribe], ["Microphone", "Audio file", "YouTube"])
-
-demo.launch(enable_queue=True)
-
+demo.launch()