benchmarks/rnnt/ootb/inference/pytorch/parts/text/cleaners.py [20:89]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
'''
Cleaners are transformations that run over the input text at both training and eval time.

Cleaners can be selected by passing a comma-delimited list of cleaner names as the "cleaners"
hyperparameter. Some cleaners are English-specific. You'll typically want to use:
    1. "english_cleaners" for English text
    2. "transliteration_cleaners" for non-English text that can be transliterated to ASCII using
         the Unidecode library (https://pypi.python.org/pypi/Unidecode)
    3. "basic_cleaners" if you do not want to transliterate (in this case, you should also update
         the symbols in symbols.py to match your data).

'''


# Regular expression matching whitespace:
import re
from unidecode import unidecode
from .numbers import normalize_numbers
_whitespace_re = re.compile(r'\s+')

# List of (regular expression, replacement) pairs for abbreviations:
_abbreviations = [(re.compile('\\b%s\\.' % x[0], re.IGNORECASE), x[1]) for x in [
    ('mrs', 'misess'),
    ('mr', 'mister'),
    ('dr', 'doctor'),
    ('st', 'saint'),
    ('co', 'company'),
    ('jr', 'junior'),
    ('maj', 'major'),
    ('gen', 'general'),
    ('drs', 'doctors'),
    ('rev', 'reverend'),
    ('lt', 'lieutenant'),
    ('hon', 'honorable'),
    ('sgt', 'sergeant'),
    ('capt', 'captain'),
    ('esq', 'esquire'),
    ('ltd', 'limited'),
    ('col', 'colonel'),
    ('ft', 'fort'),
]]


def expand_abbreviations(text):
    for regex, replacement in _abbreviations:
        text = re.sub(regex, replacement, text)
    return text


def expand_numbers(text):
    return normalize_numbers(text)


def lowercase(text):
    return text.lower()


def collapse_whitespace(text):
    return re.sub(_whitespace_re, ' ', text)


def convert_to_ascii(text):
    return unidecode(text)


def remove_punctuation(text, table):
    text = text.translate(table)
    text = re.sub(r'&', " and ", text)
    text = re.sub(r'\+', " plus ", text)
    return text
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



benchmarks/rnnt/ootb/train/common/text/cleaners.py [20:83]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
'''
Cleaners are transformations that run over the input text at both training and eval time.

Cleaners can be selected by passing a comma-delimited list of cleaner names as the "cleaners"
hyperparameter. Some cleaners are English-specific. You'll typically want to use:
    1. "english_cleaners" for English text
    2. "transliteration_cleaners" for non-English text that can be transliterated to ASCII using
         the Unidecode library (https://pypi.python.org/pypi/Unidecode)
    3. "basic_cleaners" if you do not want to transliterate (in this case, you should also update
         the symbols in symbols.py to match your data).

'''

import re
from unidecode import unidecode
from .numbers import normalize_numbers

# Regular expression matching whitespace:
_whitespace_re = re.compile(r'\s+')

# List of (regular expression, replacement) pairs for abbreviations:
_abbreviations = [(re.compile('\\b%s\\.' % x[0], re.IGNORECASE), x[1]) for x in [
    ('mrs', 'misess'),
    ('mr', 'mister'),
    ('dr', 'doctor'),
    ('st', 'saint'),
    ('co', 'company'),
    ('jr', 'junior'),
    ('maj', 'major'),
    ('gen', 'general'),
    ('drs', 'doctors'),
    ('rev', 'reverend'),
    ('lt', 'lieutenant'),
    ('hon', 'honorable'),
    ('sgt', 'sergeant'),
    ('capt', 'captain'),
    ('esq', 'esquire'),
    ('ltd', 'limited'),
    ('col', 'colonel'),
    ('ft', 'fort'),
]]

def expand_abbreviations(text):
    for regex, replacement in _abbreviations:
        text = re.sub(regex, replacement, text)
    return text

def expand_numbers(text):
    return normalize_numbers(text)

def lowercase(text):
    return text.lower()

def collapse_whitespace(text):
    return re.sub(_whitespace_re, ' ', text)

def convert_to_ascii(text):
    return unidecode(text)

def remove_punctuation(text, table):
    text = text.translate(table)
    text = re.sub(r'&', " and ", text)
    text = re.sub(r'\+', " plus ", text)
    return text
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -