model_inferences/utils/files.py

import json
from datetime import date

import webvtt


def get_seconds(time_str):
    h, m, s_ms = time_str.split(':')
    s, ms = s_ms.split('.')
    return int(h) * 3600 + int(m) * 60 + int(s) + float('0.' + ms)

def get_transcript(path):
    with open(path) as f:
        transcript = f.read()
        transcript = transcript.replace('\n', ' ')
    return transcript

def get_captions_from_vtt(path):
    vtt = webvtt.read(path)
    return [{'start': get_seconds(caption.start), 'end': get_seconds(caption.end), 'text': caption.text} for caption in vtt]

def save_summary(summary, path, filename, config):
    path.mkdir(parents=True, exist_ok=True)
    with open(path / filename, "w+") as f:
        f.write(summary)
    with open(path / "config.txt", "w+") as f:
        config["date"] = str(date.today())
        json.dump(config, f, indent=4)
    print("Saved", path / filename)