chore: import upstream snapshot with attribution

This commit is contained in:
wehub-resource-sync
2026-07-13 13:25:10 +08:00
commit c397331b1e
3684 changed files with 990993 additions and 0 deletions
@@ -0,0 +1,23 @@
import pynini
from fun_text_processing.text_normalization.en.graph_utils import DAMO_NOT_QUOTE, GraphFst
from pynini.lib import pynutil
class CardinalFst(GraphFst):
"""
Finite state transducer for verbalizing cardinal
e.g. cardinal { integer: "23" negative: "-" } -> -23
Args:
tn_cardinal_verbalizer: TN cardinal verbalizer
"""
def __init__(self, tn_cardinal_verbalizer: GraphFst, deterministic: bool = True):
super().__init__(name="cardinal", kind="verbalize", deterministic=deterministic)
self.numbers = tn_cardinal_verbalizer.numbers
optional_sign = pynini.closure(
pynutil.delete('negative: "') + DAMO_NOT_QUOTE + pynutil.delete('" '), 0, 1
)
graph = optional_sign + self.numbers
delete_tokens = self.delete_tokens(graph)
self.fst = delete_tokens.optimize()
@@ -0,0 +1,37 @@
import pynini
from fun_text_processing.text_normalization.en.graph_utils import (
DAMO_NOT_QUOTE,
GraphFst,
delete_preserve_order,
)
from pynini.lib import pynutil
class DecimalFst(GraphFst):
"""
Finite state transducer for verbalizing decimal, e.g.
decimal { negative: "true" integer_part: "12" fractional_part: "5006" quantity: "billion" } -> -12.5006 billion
Args:
tn_decimal_verbalizer: TN decimal verbalizer
"""
def __init__(self, tn_decimal_verbalizer: GraphFst, deterministic: bool = True):
super().__init__(name="decimal", kind="verbalize", deterministic=deterministic)
delete_space = pynutil.delete(" ")
optional_sign = pynini.closure(
pynutil.delete('negative: "') + DAMO_NOT_QUOTE + pynutil.delete('"') + delete_space,
0,
1,
)
optional_integer = pynini.closure(tn_decimal_verbalizer.integer, 0, 1)
optional_fractional = pynini.closure(
delete_space + pynutil.insert(",") + tn_decimal_verbalizer.fractional_default, 0, 1
)
graph = (
optional_integer + optional_fractional + tn_decimal_verbalizer.optional_quantity
).optimize()
self.numbers = optional_sign + graph
graph = self.numbers + delete_preserve_order
delete_tokens = self.delete_tokens(graph)
self.fst = delete_tokens.optimize()
@@ -0,0 +1,50 @@
import pynini
from fun_text_processing.text_normalization.en.graph_utils import DAMO_CHAR, GraphFst, delete_space
from pynini.lib import pynutil
class MeasureFst(GraphFst):
"""
Finite state transducer for verbalizing measure, e.g.
measure { cardinal { negative: "true" integer: "12" } units: "kg" } -> -12 kg
measure { decimal { integer_part: "1/2" } units: "kg" } -> 1/2 kg
measure { decimal { integer_part: "1" fractional_part: "2" quantity: "million" } units: "kg" } -> 1,2 million kg
Args:
decimal: ITN Decimal verbalizer
cardinal: ITN Cardinal verbalizer
"""
def __init__(self, decimal: GraphFst, cardinal: GraphFst, deterministic: bool = True):
super().__init__(name="measure", kind="verbalize", deterministic=deterministic)
optional_sign = pynini.closure(pynini.cross('negative: "true"', "-"), 0, 1)
unit = (
pynutil.delete("units:")
+ delete_space
+ pynutil.delete('"')
+ pynini.closure(DAMO_CHAR - " ", 1)
+ pynutil.delete('"')
+ delete_space
)
graph_decimal = (
pynutil.delete("decimal {")
+ delete_space
+ optional_sign
+ delete_space
+ decimal.numbers
+ delete_space
+ pynutil.delete("}")
)
graph_cardinal = (
pynutil.delete("cardinal {")
+ delete_space
+ optional_sign
+ delete_space
+ cardinal.numbers
+ delete_space
+ pynutil.delete("}")
)
graph = (graph_cardinal | graph_decimal) + delete_space + pynutil.insert(" ") + unit
delete_tokens = self.delete_tokens(graph)
self.fst = delete_tokens.optimize()
@@ -0,0 +1,26 @@
import pynini
from fun_text_processing.text_normalization.en.graph_utils import DAMO_CHAR, GraphFst, delete_space
from pynini.lib import pynutil
class MoneyFst(GraphFst):
"""
Finite state transducer for verbalizing money, e.g.
money { integer_part: "12" fractional_part: "05" currency: "$" } -> $12.05
Args:
decimal: ITN Decimal verbalizer
"""
def __init__(self, decimal: GraphFst, deterministic: bool = True):
super().__init__(name="money", kind="verbalize", deterministic=deterministic)
unit = (
pynutil.delete("currency:")
+ delete_space
+ pynutil.delete('"')
+ pynini.closure(DAMO_CHAR - " ", 1)
+ pynutil.delete('"')
)
graph = unit + delete_space + decimal.numbers
delete_tokens = self.delete_tokens(graph)
self.fst = delete_tokens.optimize()
@@ -0,0 +1,52 @@
import pynini
from fun_text_processing.text_normalization.en.graph_utils import (
DAMO_ALPHA,
DAMO_DIGIT,
GraphFst,
delete_space,
)
from pynini.lib import pynutil
class TimeFst(GraphFst):
"""
Finite state transducer for verbalizing time, e.g.
time { hours: "8" minutes: "30" zone: "e s t" } -> 08:30 Uhr est
time { hours: "8" } -> 8 Uhr
time { hours: "8" minutes: "30" seconds: "10" } -> 08:30:10 Uhr
"""
def __init__(self, deterministic: bool = True):
super().__init__(name="time", kind="verbalize", deterministic=deterministic)
add_leading_zero_to_double_digit = (DAMO_DIGIT + DAMO_DIGIT) | (
pynutil.insert("0") + DAMO_DIGIT
)
hour = pynutil.delete('hours: "') + pynini.closure(DAMO_DIGIT, 1) + pynutil.delete('"')
minute = pynutil.delete('minutes: "') + pynini.closure(DAMO_DIGIT, 1) + pynutil.delete('"')
second = pynutil.delete('seconds: "') + pynini.closure(DAMO_DIGIT, 1) + pynutil.delete('"')
zone = (
pynutil.delete('zone: "')
+ pynini.closure(DAMO_ALPHA + delete_space)
+ DAMO_ALPHA
+ pynutil.delete('"')
)
optional_zone = pynini.closure(pynini.accep(" ") + zone, 0, 1)
graph = (
delete_space
+ pynutil.insert(":")
+ (minute @ add_leading_zero_to_double_digit)
+ pynini.closure(
delete_space + pynutil.insert(":") + (second @ add_leading_zero_to_double_digit),
0,
1,
)
+ pynutil.insert(" Uhr")
+ optional_zone
)
graph_h = hour + pynutil.insert(" Uhr") + optional_zone
graph_hm = hour @ add_leading_zero_to_double_digit + graph
graph_hms = hour @ add_leading_zero_to_double_digit + graph
final_graph = graph_hm | graph_hms | graph_h
self.fst = self.delete_tokens(final_graph).optimize()
@@ -0,0 +1,35 @@
from fun_text_processing.inverse_text_normalization.de.verbalizers.cardinal import CardinalFst
from fun_text_processing.inverse_text_normalization.de.verbalizers.decimal import DecimalFst
from fun_text_processing.inverse_text_normalization.de.verbalizers.measure import MeasureFst
from fun_text_processing.inverse_text_normalization.de.verbalizers.money import MoneyFst
from fun_text_processing.inverse_text_normalization.de.verbalizers.time import TimeFst
from fun_text_processing.text_normalization.de.verbalizers.cardinal import (
CardinalFst as TNCardinalVerbalizer,
)
from fun_text_processing.text_normalization.de.verbalizers.decimal import (
DecimalFst as TNDecimalVerbalizer,
)
from fun_text_processing.text_normalization.en.graph_utils import GraphFst
class VerbalizeFst(GraphFst):
"""
Composes other verbalizer grammars.
For deployment, this grammar will be compiled and exported to OpenFst Finate State Archiv (FAR) File.
More details to deployment at NeMo/tools/text_processing_deployment.
"""
def __init__(self, deterministic: bool = True):
super().__init__(name="verbalize", kind="verbalize", deterministic=deterministic)
tn_cardinal_verbalizer = TNCardinalVerbalizer(deterministic=False)
tn_decimal_verbalizer = TNDecimalVerbalizer(deterministic=False)
cardinal = CardinalFst(tn_cardinal_verbalizer=tn_cardinal_verbalizer)
cardinal_graph = cardinal.fst
decimal = DecimalFst(tn_decimal_verbalizer=tn_decimal_verbalizer)
decimal_graph = decimal.fst
measure_graph = MeasureFst(decimal=decimal, cardinal=cardinal).fst
money_graph = MoneyFst(decimal=decimal).fst
time_graph = TimeFst().fst
graph = time_graph | money_graph | measure_graph | decimal_graph | cardinal_graph
self.fst = graph
@@ -0,0 +1,33 @@
import pynini
from fun_text_processing.inverse_text_normalization.de.verbalizers.verbalize import VerbalizeFst
from fun_text_processing.inverse_text_normalization.en.verbalizers.word import WordFst
from fun_text_processing.text_normalization.en.graph_utils import (
GraphFst,
delete_extra_space,
delete_space,
)
from pynini.lib import pynutil
class VerbalizeFinalFst(GraphFst):
"""
Finite state transducer that verbalizes an entire sentence, e.g.
tokens { name: "jetzt" } tokens { name: "ist" } tokens { time { hours: "12" minutes: "30" } } -> jetzt ist 12:30 Uhr
"""
def __init__(self, deterministic: bool = True):
super().__init__(name="verbalize_final", kind="verbalize", deterministic=deterministic)
verbalize = VerbalizeFst().fst
word = WordFst().fst
types = verbalize | word
graph = (
pynutil.delete("tokens")
+ delete_space
+ pynutil.delete("{")
+ delete_space
+ types
+ delete_space
+ pynutil.delete("}")
)
graph = delete_space + pynini.closure(graph + delete_extra_space) + graph + delete_space
self.fst = graph