Views
No views yet
1from transformers import AutoTokenizer
2
3gpt2_tokenizer = AutoTokenizer.from_pretrained("gpt2")
4chords_gpt2_tokenizer = AutoTokenizer.from_pretrained("lluccardoner/melodyGPT-song-chords-tokenizer-1")
5
6print(gpt2_tokenizer.vocab_size) # 50257
7print(chords_gpt2_tokenizer.vocab_size) # 19972
8
9example_chords = "Intro: Adim G7/13 Em Bb (4x) G#dim Bm/C F#m Ab|---------------------------------| (Bridge) C G Em7 Asus4"
10
11tokens = gpt2_tokenizer.tokenize(example_chords)
12# tokens: ['Int', 'ro', ':', 'ĠAd', 'im', 'ĠG', '7', '/', '13', 'ĠEm', 'ĠB', 'b', 'Ġ(', '4', 'x', ')', 'ĠG', '#', 'dim', 'ĠB', 'm', '/', 'C', 'ĠF', '#', 'm', 'ĠAb', '|', '--------------------------------', '-|', 'Ġ(', 'Bridge', ')', 'ĠC', 'ĠG', 'ĠEm', '7', 'ĠAsus', '4']
13
14new_tokens = chords_gpt2_tokenizer.tokenize(example_chords)
15# new_tokens: ['Intro', ':', 'ĠAdim', 'ĠG', '7', '/', '13', 'ĠEm', 'ĠBb', 'Ġ(', '4', 'x', ')', 'ĠG', '#', 'dim', 'ĠBm', '/', 'C', 'ĠF', '#', 'm', 'ĠAb', '|---------------------------------|', 'Ġ(', 'Bridge', ')', 'ĠC', 'ĠG', 'ĠEm', '7', 'ĠAsus', '4']