upgrade gradio and freeGPU spaces

app.py

@@ -1,4 +1,5 @@
 import torch
+import spaces
 
 import gradio as gr
 import pytube as pt
@@ -18,6 +19,7 @@ pipe = pipeline(
 
 pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language=lang, task="transcribe")
 
+@spaces.GPU
 def transcribe(microphone, file_upload):
     warn_output = ""
     if (microphone is not None) and (file_upload is not None):
@@ -61,12 +63,10 @@ demo = gr.Blocks()
 mf_transcribe = gr.Interface(
     fn=transcribe,
     inputs=[
-        gr.inputs.Audio(source="microphone", type="filepath", optional=True),
-        gr.inputs.Audio(source="upload", type="filepath", optional=True),
+        gr.Audio(sources="microphone", type="filepath"),
+        gr.Audio(sources="upload", type="filepath"),
     ],
     outputs="text",
-    layout="horizontal",
-    theme="huggingface",
     title="Whisper Demo: Transcribe Czech Audio",
     description=(
         "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the fine-tuned"
@@ -78,10 +78,8 @@ mf_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")],
+    inputs=[gr.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL")],
     outputs=["html", "text"],
-    layout="horizontal",
-    theme="huggingface",
     title="Whisper Demo: Transcribe YouTube",
     description=(
         "Transcribe long-form YouTube videos with the click of a button! Demo uses the the fine-tuned checkpoint:"
@@ -94,4 +92,4 @@ yt_transcribe = gr.Interface(
 with demo:
     gr.TabbedInterface([mf_transcribe, yt_transcribe], ["Transcribe Audio", "Transcribe YouTube"])
 
-demo.launch(enable_queue=True)
+demo.launch(server_name="0.0.0.0")

requirements.txt

@@ -1,3 +1,4 @@
 git+https://github.com/huggingface/transformers
 torch
-pytube
+pytube
+spaces