Update app.py

app.py

@@ -1,12 +1,11 @@
 import torch
-
 import gradio as gr
 import yt_dlp as youtube_dl
 from transformers import pipeline
 from transformers.pipelines.audio_utils import ffmpeg_read
-
 import tempfile
 import os
+import time
 
 MODEL_NAME = "openai/whisper-large-v3"
 BATCH_SIZE = 8
@@ -22,14 +21,12 @@ pipe = pipeline(
     device=device,
 )
 
-
-def transcribe(inputs, task):
-    if inputs is None:
+def transcribe(audio, task):
+    if audio is None:
         raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
 
-    text = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
-    return  text
-
+    text = pipe(audio, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
+    return text
 
 def _return_yt_html_embed(yt_url):
     video_id = yt_url.split("?v=")[-1]
@@ -70,7 +67,6 @@ def download_yt_audio(yt_url, filename):
         except youtube_dl.utils.ExtractorError as err:
             raise gr.Error(str(err))
 
-
 def yt_transcribe(yt_url, task, max_filesize=75.0):
     html_embed_str = _return_yt_html_embed(yt_url)
 
@@ -87,65 +83,40 @@ 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"
+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."
-    ),
-    allow_flagging="never",
-)
-
-file_transcribe = 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"),
-    ],
-    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",
-)
-
-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)
+    )
 
+    with gr.Tabs():
+        with gr.TabItem("Microphone"):
+            with gr.Row():
+                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(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])
+
+if __name__ == "__main__":
+    demo.launch(enable_queue=True)