27 lines
944 B
Python
27 lines
944 B
Python
|
import pynini
|
||
|
|
from fun_text_processing.text_normalization.en.graph_utils import DAMO_NOT_QUOTE, GraphFst
|
||
|
|
from pynini.lib import pynutil
|
||
|
|
|
||
|
|
|
||
|
|
class TelephoneFst(GraphFst):
|
||
|
|
"""
|
||
|
|
Finite state transducer for verbalizing telephone, e.g.
|
||
|
|
telephone { number_part: "uno dos tres uno dos tres cinco seis siete ocho" }
|
||
|
|
-> uno dos tres uno dos tres cinco seis siete ocho
|
||
|
|
|
||
|
|
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="telephone", kind="verbalize")
|
||
|
|
|
||
|
|
number_part = (
|
||
|
|
pynutil.delete('number_part: "')
|
||
|
|
+ pynini.closure(DAMO_NOT_QUOTE, 1)
|
||
|
|
+ pynutil.delete('"')
|
||
|
|
)
|
||
|
|
delete_tokens = self.delete_tokens(number_part)
|
||
|
|
self.fst = delete_tokens.optimize()
|