import webvtt
from tqdm import tqdm
from app.data_preparation.caption_merger.caption_merger import CaptionMerger
from app.data_preparation.caption_converter.video_caption import (
Caption,
VideoCaption,
)
from app.data_preparation.constants import (
RAW_CAPTION_FILES_PATH,
TED_CAPTIONS_DATASET_PATH,
)
from app.utils.utils import get_logger, save_as_json
logger = get_logger()
def run() -> None:
"""
Loads each caption files (extension .vtt), extracts their data and
store it into a json file
"""
logger.info("Loading text files")
caption_files = _load_caption_files_path()
logger.info("Caption files loaded")
captions = create_captions_dataset(caption_files)
save_as_json(captions, TED_CAPTIONS_DATASET_PATH)
def __init__(self):
self._logger = get_logger()