Update app.py

app.py

@@ -21,11 +21,11 @@ pipe = pipeline(
     device=device,
 )
 
-def transcribe(audio, task):
-    if audio is None:
+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(audio, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
+    text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
     return text
 
 def _return_yt_html_embed(yt_url):
@@ -83,42 +83,53 @@ def yt_transcribe(yt_url, task, max_filesize=75.0):
 
     return html_embed_str, text
 
-with gr.Blocks(theme="huggingface") as demo:
-    gr.Markdown("# Whisper Large V3: Transcribe Audio")
-    gr.Markdown(
-        "Transcribe long-form 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."
-    )
+description = (
+    "Transcribe long-form 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."
+)
+
+mf_transcribe = gr.Interface(
+    fn=transcribe,
+    inputs=[
+        gr.Audio(type="filepath"),
+        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
+    ],
+    outputs="text",
+    title="Whisper Large V3: Transcribe Audio (Microphone)",
+    description=description,
+    allow_flagging="never",
+)
+
+file_transcribe = gr.Interface(
+    fn=transcribe,
+    inputs=[
+        gr.Audio(type="filepath", label="Audio file"),
+        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
+    ],
+    outputs="text",
+    title="Whisper Large V3: Transcribe Audio (File Upload)",
+    description=description,
+    allow_flagging="never",
+)
+
+yt_transcribe = gr.Interface(
+    fn=yt_transcribe,
+    inputs=[
+        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"],
+    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 gr.Tabs():
-        with gr.TabItem("Microphone"):
-            with gr.Row():
-                mic_input = gr.Audio(type="filepath", label="Microphone Input")
-                # mic_input = gr.Audio(source="microphone", type="filepath", label="Microphone Input")
-                mic_task = gr.Radio(["transcribe", "translate"], label="Task", value="transcribe")
-            mic_output = gr.Textbox(label="Transcription")
-            mic_button = gr.Button("Transcribe")
-
-        with gr.TabItem("Audio file"):
-            with gr.Row():
-                file_input = gr.Audio(type="filepath", label="Audio file")
-                # file_input = gr.Audio(source="upload", type="filepath", label="Audio file")
-                file_task = gr.Radio(["transcribe", "translate"], label="Task", value="transcribe")
-            file_output = gr.Textbox(label="Transcription")
-            file_button = gr.Button("Transcribe")
-
-        with gr.TabItem("YouTube"):
-            with gr.Row():
-                yt_input = gr.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL")
-                yt_task = gr.Radio(["transcribe", "translate"], label="Task", value="transcribe")
-            yt_embed = gr.HTML(label="Video")
-            yt_output = gr.Textbox(label="Transcription")
-            yt_button = gr.Button("Transcribe")
-
-    mic_button.click(transcribe, inputs=[mic_input, mic_task], outputs=mic_output)
-    file_button.click(transcribe, inputs=[file_input, file_task], outputs=file_output)
-    yt_button.click(yt_transcribe, inputs=[yt_input, yt_task], outputs=[yt_embed, yt_output])
+demo = gr.TabbedInterface([mf_transcribe, file_transcribe, yt_transcribe], ["Microphone", "Audio file", "YouTube"])
 
 if __name__ == "__main__":
-    demo.launch(enable_queue=True)
+    demo.launch()