def __init__(self, input_case: str, lang: str = 'en'):
super().__init__(input_case=input_case, lang=lang)
if lang == 'en':
from nemo_text_processing.text_normalization.en.taggers.tokenize_and_classify import ClassifyFst
from nemo_text_processing.text_normalization.en.verbalizers.verbalize_final import VerbalizeFinalFst
self.tagger = ClassifyFst(input_case=input_case, deterministic=False)
self.verbalizer = VerbalizeFinalFst(deterministic=False)
def __init__(
self,
input_case: str,
lang: str = 'en',
deterministic: bool = True,
cache_dir: str = None,
overwrite_cache: bool = False,
):
assert input_case in ["lower_cased", "cased"]
if lang == 'en' and deterministic:
from nemo_text_processing.text_normalization.en.taggers.tokenize_and_classify import ClassifyFst
from nemo_text_processing.text_normalization.en.verbalizers.verbalize_final import VerbalizeFinalFst
elif lang == 'en' and not deterministic:
from nemo_text_processing.text_normalization.en.taggers.tokenize_and_classify_with_audio import ClassifyFst
from nemo_text_processing.text_normalization.en.verbalizers.verbalize_final import VerbalizeFinalFst
elif lang == 'ru':
# Ru TN only support non-deterministic cases and produces multiple normalization options
# use normalize_with_audio.py
from nemo_text_processing.text_normalization.ru.taggers.tokenize_and_classify import ClassifyFst
from nemo_text_processing.text_normalization.ru.verbalizers.verbalize_final import VerbalizeFinalFst
self.tagger = ClassifyFst(input_case=input_case,
deterministic=deterministic,
cache_dir=cache_dir,
overwrite_cache=overwrite_cache)
self.verbalizer = VerbalizeFinalFst(deterministic=deterministic)
self.parser = TokenParser()
self.lang = lang
def __init__(self, input_case: str, lang: str = 'en'):
assert input_case in ["lower_cased", "cased"]
if lang == 'en':
from nemo_text_processing.text_normalization.en.taggers.tokenize_and_classify import ClassifyFst
from nemo_text_processing.text_normalization.en.verbalizers.verbalize_final import VerbalizeFinalFst
self.tagger = ClassifyFst(input_case=input_case, deterministic=True)
self.verbalizer = VerbalizeFinalFst(deterministic=True)
self.parser = TokenParser()
def __init__(
self,
input_case: str,
lang: str = 'en',
deterministic: bool = True,
cache_dir: str = None,
overwrite_cache: bool = False,
whitelist: str = None,
lm: bool = False,
):
assert input_case in ["lower_cased", "cased"]
if not PYNINI_AVAILABLE:
raise ImportError(get_installation_msg())
if lang == 'en' and deterministic:
from nemo_text_processing.text_normalization.en.taggers.tokenize_and_classify import ClassifyFst
from nemo_text_processing.text_normalization.en.verbalizers.verbalize_final import VerbalizeFinalFst
elif lang == 'en' and not deterministic:
if lm:
from nemo_text_processing.text_normalization.en.taggers.tokenize_and_classify_lm import ClassifyFst
else:
from nemo_text_processing.text_normalization.en.taggers.tokenize_and_classify_with_audio import (
ClassifyFst, )
from nemo_text_processing.text_normalization.en.verbalizers.verbalize_final import VerbalizeFinalFst
elif lang == 'ru':
# Ru TN only support non-deterministic cases and produces multiple normalization options
# use normalize_with_audio.py
from nemo_text_processing.text_normalization.ru.taggers.tokenize_and_classify import ClassifyFst
from nemo_text_processing.text_normalization.ru.verbalizers.verbalize_final import VerbalizeFinalFst
elif lang == 'de':
from nemo_text_processing.text_normalization.de.taggers.tokenize_and_classify import ClassifyFst
from nemo_text_processing.text_normalization.de.verbalizers.verbalize_final import VerbalizeFinalFst
elif lang == 'es':
from nemo_text_processing.text_normalization.es.taggers.tokenize_and_classify import ClassifyFst
from nemo_text_processing.text_normalization.es.verbalizers.verbalize_final import VerbalizeFinalFst
self.tagger = ClassifyFst(
input_case=input_case,
deterministic=deterministic,
cache_dir=cache_dir,
overwrite_cache=overwrite_cache,
whitelist=whitelist,
)
self.verbalizer = VerbalizeFinalFst(deterministic=deterministic)
self.parser = TokenParser()
self.lang = lang
if NLP_AVAILABLE:
self.processor = MosesProcessor(lang_id=lang)
else:
self.processor = None
print(
"NeMo NLP is not available. Moses de-tokenization will be skipped."
)
def __init__(self, input_case: str, lang: str = 'en', cache_dir: str = None, overwrite_cache: bool = False):
if lang == 'en':
from nemo_text_processing.text_normalization.en.taggers.tokenize_and_classify_with_audio import ClassifyFst
from nemo_text_processing.text_normalization.en.verbalizers.verbalize_final import VerbalizeFinalFst
self.tagger = ClassifyFst(
input_case=input_case, deterministic=False, cache_dir=cache_dir, overwrite_cache=overwrite_cache
)
self.verbalizer = VerbalizeFinalFst(deterministic=False)
else:
super().__init__(input_case=input_case, lang=lang, deterministric=False)
self.lang = lang
def __init__(
self,
input_case: str,
lang: str = 'en',
deterministric: bool = True,
cache_dir: str = None,
overwrite_cache: bool = False,
):
assert input_case in ["lower_cased", "cased"]
if lang == 'en':
from nemo_text_processing.text_normalization.en.taggers.tokenize_and_classify import ClassifyFst
from nemo_text_processing.text_normalization.en.verbalizers.verbalize_final import VerbalizeFinalFst
self.tagger = ClassifyFst(input_case=input_case,
deterministic=deterministric,
cache_dir=cache_dir,
overwrite_cache=overwrite_cache)
self.verbalizer = VerbalizeFinalFst(deterministic=deterministric)
self.parser = TokenParser()