Update app.py

app.py

@@ -1,11 +1,10 @@
 import torch
-
 import gradio as gr
 import pytube as pt
 from transformers import pipeline
 from huggingface_hub import model_info
 
-MODEL_NAME = "BlueRaccoon/whisper-small-kab" #this always needs to stay in line 8 :D sorry for the hackiness
+MODEL_NAME = "BlueRaccoon/whisper-small-kab"  # this always needs to stay in line 8 :D sorry for the hackiness
 lang = "uz"
 
 device = 0 if torch.cuda.is_available() else "cpu"
@@ -18,6 +17,7 @@ pipe = pipeline(
 
 pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language=lang, task="transcribe")
 
+
 def transcribe(microphone, file_upload):
     warn_output = ""
     if (microphone is not None) and (file_upload is not None):
@@ -56,42 +56,42 @@ def yt_transcribe(yt_url):
     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.Audio(source="upload", type="filepath", optional=True),
-    ],
-    outputs="text",
-    layout="horizontal",
-    theme="huggingface",
-    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 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:"
-        f" [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files of"
-        " arbitrary length."
-    ),
-    allow_flagging="never",
-)
+with gr.Blocks() as demo:
+    with gr.Tab("Transcribe Audio"):
+        gr.Markdown(
+            f"""
+            # Whisper Demo: Transcribe Audio
+            Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the fine-tuned
+            checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files
+            of arbitrary length.
+            """
+        )
+        audio_inputs = [
+            gr.Audio(source="microphone", type="filepath", label="Record from Microphone"),
+            gr.Audio(source="upload", type="filepath", label="Upload Audio File"),
+        ]
+        gr.Interface(
+            fn=transcribe,
+            inputs=audio_inputs,
+            outputs=gr.Textbox(label="Transcription"),
+            live=False,
+        )
 
-with demo:
-    gr.TabbedInterface([mf_transcribe, yt_transcribe], ["Transcribe Audio", "Transcribe YouTube"])
+    with gr.Tab("Transcribe YouTube"):
+        gr.Markdown(
+            f"""
+            # Whisper Demo: Transcribe YouTube
+            Transcribe long-form YouTube videos with the click of a button! Demo uses the fine-tuned checkpoint
+            [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files of
+            arbitrary length.
+            """
+        )
+        yt_url_input = gr.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL")
+        gr.Interface(
+            fn=yt_transcribe,
+            inputs=[yt_url_input],
+            outputs=[gr.HTML(label="YouTube Video"), gr.Textbox(label="Transcription")],
+            live=False,
+        )
 
 demo.launch(enable_queue=True)