Grapheme label error

[upskyy]

Information

The graphene label value needs to be corrected.

def generate_grapheme_labels(grapheme_transcripts, vocab_path: str):
    vocab_list = list()
    vocab_freq = list()

    for grapheme_transcript in grapheme_transcripts:
        graphemes = grapheme_transcript.split()
        for grapheme in graphemes:
            if grapheme not in vocab_list:
                vocab_list.append(grapheme)
                vocab_freq.append(1)
            else:
                vocab_freq[vocab_list.index(grapheme)] += 1

    vocab_freq, vocab_list = zip(*sorted(zip(vocab_freq, vocab_list), reverse=True))
    vocab_dict = {
        'id': [0, 1, 2, 3],
        'grpm': ['<pad>', '<sos>', '<eos>', '<blank>'],
        'freq': [0, 0, 0, 0]
    }

    for idx, (grpm, freq) in enumerate(zip(vocab_list, vocab_freq)):
        vocab_dict['id'].append(idx + 3)
        vocab_dict['grpm'].append(grpm)
        vocab_dict['freq'].append(freq)

    label_df = pd.DataFrame(vocab_dict)
    label_df.to_csv(vocab_path, encoding="utf-8", index=False)

Expected behavior

vocab_dict['id'].append(idx + 3) -> vocab_dict['id'].append(idx + 4)