Spaces:
Sleeping
Sleeping
Delete text.py
Browse files
text.py
DELETED
|
@@ -1,92 +0,0 @@
|
|
| 1 |
-
# """ from https://github.com/keithito/tacotron """
|
| 2 |
-
|
| 3 |
-
# """
|
| 4 |
-
# Cleaners are transformations that run over the input text at both training and eval time.
|
| 5 |
-
|
| 6 |
-
# Cleaners can be selected by passing a comma-delimited list of cleaner names as the "cleaners"
|
| 7 |
-
# hyperparameter. Some cleaners are English-specific. You'll typically want to use:
|
| 8 |
-
# 1. "english_cleaners" for English text
|
| 9 |
-
# 2. "transliteration_cleaners" for non-English text that can be transliterated to ASCII using
|
| 10 |
-
# the Unidecode library (https://pypi.python.org/pypi/Unidecode)
|
| 11 |
-
# 3. "basic_cleaners" if you do not want to transliterate (in this case, you should also update
|
| 12 |
-
# the symbols in symbols.py to match your data).
|
| 13 |
-
# """
|
| 14 |
-
|
| 15 |
-
# import re
|
| 16 |
-
# from mynumbers import normalize_numbers
|
| 17 |
-
# from unidecode import unidecode
|
| 18 |
-
|
| 19 |
-
# # Regular expression matching whitespace:
|
| 20 |
-
# _whitespace_re = re.compile(r"\s+")
|
| 21 |
-
|
| 22 |
-
# # List of (regular expression, replacement) pairs for abbreviations:
|
| 23 |
-
# _abbreviations = [
|
| 24 |
-
# (re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
|
| 25 |
-
# for x in [
|
| 26 |
-
# ("mrs", "misess"),
|
| 27 |
-
# ("mr", "mister"),
|
| 28 |
-
# ("dr", "doctor"),
|
| 29 |
-
# ("st", "saint"),
|
| 30 |
-
# ("co", "company"),
|
| 31 |
-
# ("jr", "junior"),
|
| 32 |
-
# ("maj", "major"),
|
| 33 |
-
# ("gen", "general"),
|
| 34 |
-
# ("drs", "doctors"),
|
| 35 |
-
# ("rev", "reverend"),
|
| 36 |
-
# ("lt", "lieutenant"),
|
| 37 |
-
# ("hon", "honorable"),
|
| 38 |
-
# ("sgt", "sergeant"),
|
| 39 |
-
# ("capt", "captain"),
|
| 40 |
-
# ("esq", "esquire"),
|
| 41 |
-
# ("ltd", "limited"),
|
| 42 |
-
# ("col", "colonel"),
|
| 43 |
-
# ("ft", "fort"),
|
| 44 |
-
# ]
|
| 45 |
-
# ]
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
# def expand_abbreviations(text):
|
| 49 |
-
# for regex, replacement in _abbreviations:
|
| 50 |
-
# text = re.sub(regex, replacement, text)
|
| 51 |
-
# return text
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
# def expand_numbers(text):
|
| 55 |
-
# return normalize_numbers(text)
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
# def lowercase(text):
|
| 59 |
-
# return text.lower()
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
# def collapse_whitespace(text):
|
| 63 |
-
# return re.sub(_whitespace_re, " ", text)
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
# def convert_to_ascii(text):
|
| 67 |
-
# return unidecode(text)
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
# def basic_cleaners(text):
|
| 71 |
-
# """Basic pipeline that lowercases and collapses whitespace without transliteration."""
|
| 72 |
-
# text = lowercase(text)
|
| 73 |
-
# text = collapse_whitespace(text)
|
| 74 |
-
# return text
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
# def transliteration_cleaners(text):
|
| 78 |
-
# """Pipeline for non-English text that transliterates to ASCII."""
|
| 79 |
-
# text = convert_to_ascii(text)
|
| 80 |
-
# text = lowercase(text)
|
| 81 |
-
# text = collapse_whitespace(text)
|
| 82 |
-
# return text
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
# def english_cleaners(text):
|
| 86 |
-
# """Pipeline for English text, including number and abbreviation expansion."""
|
| 87 |
-
# text = convert_to_ascii(text)
|
| 88 |
-
# text = lowercase(text)
|
| 89 |
-
# text = expand_numbers(text)
|
| 90 |
-
# text = expand_abbreviations(text)
|
| 91 |
-
# text = collapse_whitespace(text)
|
| 92 |
-
# return text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|