FunASR/fun_text_processing/text_normalization/es/verbalizers/cardinal.py

48 lines
1.8 KiB
Python
Raw Normal View History

2024-05-18 15:50:56 +08:00
import pynini
from fun_text_processing.text_normalization.en.graph_utils import DAMO_NOT_QUOTE, GraphFst
from fun_text_processing.text_normalization.es.graph_utils import (
add_cardinal_apocope_fem,
shift_cardinal_gender,
strip_cardinal_apocope,
)
from pynini.lib import pynutil
class CardinalFst(GraphFst):
"""
Finite state transducer for verbalizing cardinals
e.g. cardinal { integer: "dos" } -> "dos"
Args:
deterministic: if True will provide a single transduction option,
for False multiple transduction are generated (used for audio-based normalization)
"""
def __init__(self, deterministic: bool = True):
super().__init__(name="cardinal", kind="verbalize", deterministic=deterministic)
optional_sign = pynini.closure(pynini.cross('negative: "true" ', "menos "), 0, 1)
self.optional_sign = optional_sign
integer = pynini.closure(DAMO_NOT_QUOTE, 1)
self.integer = pynutil.delete(' "') + integer + pynutil.delete('"')
integer = pynutil.delete("integer:") + self.integer
graph_masc = optional_sign + integer
graph_fem = shift_cardinal_gender(graph_masc)
self.graph_masc = pynini.optimize(graph_masc)
self.graph_fem = pynini.optimize(graph_fem)
# Adding adjustment for fem gender (choice of gender will be random)
graph = graph_masc | graph_fem
if not deterministic:
# For alternate renderings when apocope is omitted (i.e. cardinal stands alone)
graph |= strip_cardinal_apocope(graph_masc)
# "una" will drop to "un" in unique contexts
graph |= add_cardinal_apocope_fem(graph_fem)
delete_tokens = self.delete_tokens(graph)
self.fst = delete_tokens.optimize()