from transformers import pipeline
import gradio as gr
from pytube import YouTube
import os

pipe = pipeline(model="afroanton/whisper-small-sv-SE")  # change to "your-username/the-name-you-picked"

def transcribe(audio):
    text = pipe(audio)["text"]
    return text

def transcribeUrl(url):
    yt = YouTube(str(url))
    audio = yt.streams.filter(only_audio=True).first()
    text = pipe(audio)["text"]
    return text
    
video_demo = gr.Interface.load(
    fn=transcribeUrl, 
    inputs=gr.Textbox(
            label="insert URL",
            lines=3,
            value="The fast brown fox jumps over lazy dogs.",
        ), 
    outputs="text",
    title="Whisper Small Swedish",
    description="Realtime demo for Swedish speech recognition using a fine-tuned Whisper small model.",
)

voice_demo = gr.Interface(
    fn=transcribe, 
    inputs=gr.Audio(source="microphone", type="filepath"), 
    outputs="text",
    title="Whisper Small Swedish",
    description="Realtime demo for Swedish speech recognition using a fine-tuned Whisper small model.",
)

demo = gr.TabbedInterface([voice_demo, video_demo], ["voice to text", "video to text"])

demo.launch()