import gradio as gr
import whisper
from pytube import YouTube
import yake
from transformers import pipeline

class GradioInference():
    def __init__(self):
        self.sizes = list(whisper._MODELS.keys())
        self.langs = ["none"] + sorted(list(whisper.tokenizer.LANGUAGES.values()))
        self.current_size = "base"
        self.loaded_model = whisper.load_model(self.current_size)
        self.yt = None

        # Initialize YAKE keyword extractor
        self.keyword_extractor = yake.KeywordExtractor(lan="en", n=3, dedupLim=0.9, dedupFunc="seqm", windowsSize=1, top=5, features=None)

        # Initialize Facebook/BART-Large-CNN summarizer
        self.summarizer = pipeline("summarization", model="facebook/bart-large-cnn")

    def __call__(self, link, lang, size):
        if self.yt is None:
            self.yt = YouTube(link)
        path = self.yt.streams.filter(only_audio=True)[0].download(filename="tmp.mp4")

        if lang == "none":
            lang = None

        if size != self.current_size:
            self.loaded_model = whisper.load_model(size)
            self.current_size = size
        results = self.loaded_model.transcribe(path, language=lang)

        # Perform summarization on the transcription
        transcription_summary = self.summarizer(results["text"], max_length=130, min_length=30, do_sample=False)

        # Extract keywords from the transcription
        keywords = self.keyword_extractor.extract_keywords(results["text"])

        return results["text"], transcription_summary[0]["summary_text"], [kw[0] for kw in keywords]

    def populate_metadata(self, link):
        self.yt = YouTube(link)
        return self.yt.thumbnail_url, self.yt.title


gio = GradioInference()
title = "Youtube Whisperer"
description = "Speech to text transcription, summary, and keyword extraction of Youtube videos using OpenAI's Whisper, Facebook/BART-Large-CNN, and YAKE"

block = gr.Blocks()
with block:
    gr.HTML(
        """
        <div style="text-align: center; max-width: 500px; margin: 0 auto;">
          <div>
            <h1>Youtube Whisperer</h1>
          </div>
          <p style="margin-bottom: 10px; font-size: 94%">
            Speech to text transcription, summary, and keyword extraction of Youtube videos using OpenAI's Whisper, Facebook/BART-Large-CNN, and YAKE
          </p>
        </div>
        """
    )
    with gr.Group():
        with gr.Box():
            with gr.Row().style(equal_height=True):
                sz = gr.Dropdown(label="Model Size", choices=gio.sizes, value='base')
                lang = gr.Dropdown(label="Language (Optional)", choices=gio.langs, value="none")
            link = gr.Textbox(label="YouTube Link")
            title = gr.Label(label="Video Title")
            with gr.Row().style(equal_height=True):
                img = gr.Image(label="Thumbnail")
                text = gr.Textbox(label="Transcription", placeholder="Transcription Output", lines=10)
            with gr.Row().style(equal_height=True):
                summary = gr.Textbox(label="Summary", placeholder="Summary Output", lines=5)
                keywords = gr.Textbox(label="Keywords", placeholder="Keywords Output", lines=5)
            with gr.Row().style(equal_height=True):
                btn = gr.Button("Transcribe, Summarize & Extract Keywords")
            btn.click(gio, inputs=[link, lang, sz], outputs=[text, summary, keywords])
            link.change(gio.populate_metadata, inputs=[link], outputs=[img, title])

block.launch()