import json, glob

for fname in glob.glob('transcripts/ep*.json'):
    with open(fname, 'r', encoding='utf-8') as f:
        data = json.load(f)
        for seg in data['segments']:
            text = seg['text']
            for c in text:
                if ord(c) > 127:
                    print(f'{data["ep_num"]}: {repr(c)} U+{ord(c):04X} in: {seg["text"][:80]}')
                    break