app.py

import gradio as gr
import spaces
from utils import MODEL_NAME
from transcribe import transcribe
from youtube import yt_transcribe

demo = gr.Blocks()

mf_transcribe = gr.Interface(
    fn=spaces.GPU(transcribe),
    inputs=[
        gr.Audio(sources="microphone", type="filepath"),
        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
    ],
    outputs="text",
    title="Whisper Large V3: Transcribe Audio",
    description=(
        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the"
        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=spaces.GPU(transcribe),
    inputs=[
        gr.Audio(sources="upload", type="filepath", label="Audio file"),
        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
    ],
    outputs="text",
    title="Whisper Large V3: Transcribe Audio",
    description=(
        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the"
        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
        " of arbitrary length."
    ),
    allow_flagging="never",
)

yt_transcribe_interface = gr.Interface(
    fn=spaces.GPU(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 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_interface], ["Microphone", "Audio file", "YouTube"])

demo.queue().launch()