musicaiz.tokenizers.EncodeBase¶
- class musicaiz.tokenizers.EncodeBase[source]¶
- __init__(*args, **kwargs)¶
Methods
__init__(*args, **kwargs)add_token_to_vocabulary()get_vocabulary([vocab_filename])This method gets the vocabulary of a tokenize dataset in all the token-sequences.txt files in the directory dataset_path.
to_txt(all_files_tokens, file_name, path)