paddlespeech.t2s.frontend.vocab module

class paddlespeech.t2s.frontend.vocab.Vocab(symbols: Iterable[str], padding_symbol='<pad>', unk_symbol='<unk>', start_symbol='<s>', end_symbol='</s>')[source]

Bases: object

Vocabulary.

Args:: symbols (Iterable[str]): Common symbols. padding_symbol (str, optional): Symbol for pad. Defaults to "<pad>". unk_symbol (str, optional): Symbol for unknow. Defaults to "<unk>" start_symbol (str, optional): Symbol for start. Defaults to "<s>" end_symbol (str, optional): Symbol for end. Defaults to "</s>"

Attributes:

end_index: The index of end symbol.
num_specials: The number of special symbols.
padding_index: The index of padding symbol
start_index: The index of start symbol.
unk_index: The index of unknow symbol.

Methods

`add_symbol`(symbol)	Add a new symbol in vocab.
`add_symbols`(symbols)	Add multiple symbols in vocab.
`lookup`(symbol)	The index that symbol correspond.
`reverse`(index)	The symbol thar index cottespond.

add_symbol(symbol)[source]: Add a new symbol in vocab.

add_symbols(symbols)[source]: Add multiple symbols in vocab.

property end_index: The index of end symbol.

lookup(symbol)[source]: The index that symbol correspond.

property num_specials: The number of special symbols.

property padding_index: The index of padding symbol

reverse(index)[source]: The symbol thar index cottespond.

property start_index: The index of start symbol.

property unk_index: The index of unknow symbol.