import logging
import warnings

import gradio as gr
import pytube as pt
import torch
from huggingface_hub import hf_hub_download, model_info
from transformers.utils.logging import disable_progress_bar
import whisper


warnings.filterwarnings("ignore")
disable_progress_bar()

logging.basicConfig(
    format="%(asctime)s [%(levelname)s] [%(name)s] %(message)s",
    datefmt="%Y-%m-%dT%H:%M:%SZ",
)
logger = logging.getLogger(__name__)
logger.setLevel(logging.DEBUG)

MODEL_NAME = "bofenghuang/whisper-large-v2-cv11-french"
CHECKPOINT_FILENAME = "checkpoint_openai.pt"

GEN_KWARGS = {
    "task": "transcribe",
    "language": "fr",
    # "without_timestamps": True,
    # decode options
    # "beam_size": 5,
    # "patience": 2,
    # disable fallback
    # "compression_ratio_threshold": None,
    # "logprob_threshold": None,
    # vad threshold
    # "no_speech_threshold": None,
}

# device = 0 if torch.cuda.is_available() else "cpu"
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")


downloaded_model_path = hf_hub_download(repo_id=MODEL_NAME, filename=CHECKPOINT_FILENAME)

model = whisper.load_model(downloaded_model_path, device=device)
logger.info(f"Model has been loaded on device `{device}`")


def transcribe(microphone, file_upload):
    warn_output = ""
    if (microphone is not None) and (file_upload is not None):
        warn_output = (
            "WARNING: You've uploaded an audio file and used the microphone. "
            "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
        )

    elif (microphone is None) and (file_upload is None):
        return "ERROR: You have to either use the microphone or upload an audio file"

    file = microphone if microphone is not None else file_upload

    text = model.transcribe(file, **GEN_KWARGS)["text"]

    logger.info(f"Transcription: {text}")

    return warn_output + text


def _return_yt_html_embed(yt_url):
    video_id = yt_url.split("?v=")[-1]
    HTML_str = (
        f'<center> <iframe width="500" height="320" src="https://www.youtube.com/embed/{video_id}"> </iframe>' " </center>"
    )
    return HTML_str


def yt_transcribe(yt_url):
    yt = pt.YouTube(yt_url)
    html_embed_str = _return_yt_html_embed(yt_url)
    stream = yt.streams.filter(only_audio=True)[0]
    stream.download(filename="audio.mp3")

    text = model.transcribe("audio.mp3", **GEN_KWARGS)["text"]

    logger.info(f'Transcription of "{yt_url}": {text}')

    return html_embed_str, text


demo = gr.Blocks()

mf_transcribe = gr.Interface(
    fn=transcribe,
    inputs=[
        gr.inputs.Audio(source="microphone", type="filepath", optional=True, label="Record"),
        gr.inputs.Audio(source="upload", type="filepath", optional=True, label="Upload File"),
    ],
    # outputs="text",
    outputs=gr.outputs.Textbox(label="Transcription"),
    layout="horizontal",
    theme="huggingface",
    title="Whisper French 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"],
    outputs=[
        gr.outputs.HTML(label="YouTube Page"),
        gr.outputs.Textbox(label="Transcription"),
    ],
    layout="horizontal",
    theme="huggingface",
    title="Whisper French 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 demo:
    gr.TabbedInterface([mf_transcribe, yt_transcribe], ["Transcribe Audio", "Transcribe YouTube"])

# demo.launch(server_name="0.0.0.0", debug=True, share=True)
demo.launch(enable_queue=True)