File size: 2,911 Bytes
9b2107c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 |
# -*- coding: utf-8 -*-
import re
VALID_SYMBOLS = [
"AA",
"AA0",
"AA1",
"AA2",
"AE",
"AE0",
"AE1",
"AE2",
"AH",
"AH0",
"AH1",
"AH2",
"AO",
"AO0",
"AO1",
"AO2",
"AW",
"AW0",
"AW1",
"AW2",
"AY",
"AY0",
"AY1",
"AY2",
"B",
"CH",
"D",
"DH",
"EH",
"EH0",
"EH1",
"EH2",
"ER",
"ER0",
"ER1",
"ER2",
"EY",
"EY0",
"EY1",
"EY2",
"F",
"G",
"HH",
"IH",
"IH0",
"IH1",
"IH2",
"IY",
"IY0",
"IY1",
"IY2",
"JH",
"K",
"L",
"M",
"N",
"NG",
"OW",
"OW0",
"OW1",
"OW2",
"OY",
"OY0",
"OY1",
"OY2",
"P",
"R",
"S",
"SH",
"T",
"TH",
"UH",
"UH0",
"UH1",
"UH2",
"UW",
"UW0",
"UW1",
"UW2",
"V",
"W",
"Y",
"Z",
"ZH",
]
class CMUDict:
"""Thin wrapper around CMUDict data. http://www.speech.cs.cmu.edu/cgi-bin/cmudict"""
def __init__(self, file_or_path, keep_ambiguous=True):
if isinstance(file_or_path, str):
with open(file_or_path, encoding="latin-1") as f:
entries = _parse_cmudict(f)
else:
entries = _parse_cmudict(file_or_path)
if not keep_ambiguous:
entries = {word: pron for word, pron in entries.items() if len(pron) == 1}
self._entries = entries
def __len__(self):
return len(self._entries)
def lookup(self, word):
"""Returns list of ARPAbet pronunciations of the given word."""
return self._entries.get(word.upper())
@staticmethod
def get_arpabet(word, cmudict, punctuation_symbols):
first_symbol, last_symbol = "", ""
if word and word[0] in punctuation_symbols:
first_symbol = word[0]
word = word[1:]
if word and word[-1] in punctuation_symbols:
last_symbol = word[-1]
word = word[:-1]
arpabet = cmudict.lookup(word)
if arpabet is not None:
return first_symbol + "{%s}" % arpabet[0] + last_symbol
return first_symbol + word + last_symbol
_alt_re = re.compile(r"\([0-9]+\)")
def _parse_cmudict(file):
cmudict = {}
for line in file:
if line and (line[0] >= "A" and line[0] <= "Z" or line[0] == "'"):
parts = line.split(" ")
word = re.sub(_alt_re, "", parts[0])
pronunciation = _get_pronunciation(parts[1])
if pronunciation:
if word in cmudict:
cmudict[word].append(pronunciation)
else:
cmudict[word] = [pronunciation]
return cmudict
def _get_pronunciation(s):
parts = s.strip().split(" ")
for part in parts:
if part not in VALID_SYMBOLS:
return None
return " ".join(parts)
|