Hugging Face's logo

antoniomae1234
/
voice-xtts2

Model card Files Community
voice-xtts2
File size: 8,738 Bytes 
2493d72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
 
import os
# pylint: disable=unused-wildcard-import
# pylint: disable=wildcard-import
# pylint: disable=unused-import
import unittest
from tests import get_tests_input_path
from TTS.tts.utils.text import *
from tests import get_tests_path
from TTS.utils.io import load_config

conf = load_config(os.path.join(get_tests_input_path(), 'test_config.json'))

def test_phoneme_to_sequence():

    text = "Recent research at Harvard has shown meditating for as little as 8 weeks can actually increase, the grey matter in the parts of the brain responsible for emotional regulation and learning!"
    text_cleaner = ["phoneme_cleaners"]
    lang = "en-us"
    sequence = phoneme_to_sequence(text, text_cleaner, lang)
    text_hat = sequence_to_phoneme(sequence)
    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
    text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters)
    gt = "ɹiːsənt ɹɪsɜːtʃ æt hɑːɹvɚd hɐz ʃoʊn mɛdᵻteɪɾɪŋ fɔːɹ æz lɪɾəl æz eɪt wiːks kæn æktʃuːəli ɪnkɹiːs, ðə ɡɹeɪ mæɾɚɹ ɪnðə pɑːɹts ʌvðə bɹeɪn ɹɪspɑːnsəbəl fɔːɹ ɪmoʊʃənəl ɹɛɡjuːleɪʃən ænd lɜːnɪŋ!"
    assert text_hat == text_hat_with_params == gt
    
    # multiple punctuations
    text = "Be a voice, not an! echo?"
    sequence = phoneme_to_sequence(text, text_cleaner, lang)
    text_hat = sequence_to_phoneme(sequence)
    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
    text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters)
    gt = "biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ?"
    print(text_hat)
    print(len(sequence))
    assert text_hat == text_hat_with_params == gt

    # not ending with punctuation
    text = "Be a voice, not an! echo"
    sequence = phoneme_to_sequence(text, text_cleaner, lang)
    text_hat = sequence_to_phoneme(sequence)
    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
    text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters)
    gt = "biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ"
    print(text_hat)
    print(len(sequence))
    assert text_hat == text_hat_with_params == gt

    # original
    text = "Be a voice, not an echo!"
    sequence = phoneme_to_sequence(text, text_cleaner, lang)
    text_hat = sequence_to_phoneme(sequence)
    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
    text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters)
    gt = "biː ɐ vɔɪs, nɑːt ɐn ɛkoʊ!"
    print(text_hat)
    print(len(sequence))
    assert text_hat == text_hat_with_params == gt

    # extra space after the sentence
    text = "Be a voice, not an! echo.  "
    sequence = phoneme_to_sequence(text, text_cleaner, lang)
    text_hat = sequence_to_phoneme(sequence)
    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
    text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters)
    gt = "biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ."
    print(text_hat)
    print(len(sequence))
    assert text_hat == text_hat_with_params == gt

    # extra space after the sentence
    text = "Be a voice, not an! echo.  "
    sequence = phoneme_to_sequence(text, text_cleaner, lang, True)
    text_hat = sequence_to_phoneme(sequence)
    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
    text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters)
    gt = "^biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ.~"
    print(text_hat)
    print(len(sequence))
    assert text_hat == text_hat_with_params == gt

    # padding char
    text = "_Be a _voice, not an! echo_"
    sequence = phoneme_to_sequence(text, text_cleaner, lang)
    text_hat = sequence_to_phoneme(sequence)
    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters)
    text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters)
    gt = "biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ"
    print(text_hat)
    print(len(sequence))
    assert text_hat == text_hat_with_params == gt

def test_phoneme_to_sequence_with_blank_token():

    text = "Recent research at Harvard has shown meditating for as little as 8 weeks can actually increase, the grey matter in the parts of the brain responsible for emotional regulation and learning!"
    text_cleaner = ["phoneme_cleaners"]
    lang = "en-us"
    sequence = phoneme_to_sequence(text, text_cleaner, lang)
    text_hat = sequence_to_phoneme(sequence)
    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters, add_blank=True)
    text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters, add_blank=True)
    gt = "ɹiːsənt ɹɪsɜːtʃ æt hɑːɹvɚd hɐz ʃoʊn mɛdᵻteɪɾɪŋ fɔːɹ æz lɪɾəl æz eɪt wiːks kæn æktʃuːəli ɪnkɹiːs, ðə ɡɹeɪ mæɾɚɹ ɪnðə pɑːɹts ʌvðə bɹeɪn ɹɪspɑːnsəbəl fɔːɹ ɪmoʊʃənəl ɹɛɡjuːleɪʃən ænd lɜːnɪŋ!"
    assert text_hat == text_hat_with_params == gt

    # multiple punctuations
    text = "Be a voice, not an! echo?"
    sequence = phoneme_to_sequence(text, text_cleaner, lang)
    text_hat = sequence_to_phoneme(sequence)
    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters, add_blank=True)
    text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters, add_blank=True)
    gt = "biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ?"
    print(text_hat)
    print(len(sequence))
    assert text_hat == text_hat_with_params == gt

    # not ending with punctuation
    text = "Be a voice, not an! echo"
    sequence = phoneme_to_sequence(text, text_cleaner, lang)
    text_hat = sequence_to_phoneme(sequence)
    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters, add_blank=True)
    text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters, add_blank=True)
    gt = "biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ"
    print(text_hat)
    print(len(sequence))
    assert text_hat == text_hat_with_params == gt

    # original
    text = "Be a voice, not an echo!"
    sequence = phoneme_to_sequence(text, text_cleaner, lang)
    text_hat = sequence_to_phoneme(sequence)
    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters, add_blank=True)
    text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters, add_blank=True)
    gt = "biː ɐ vɔɪs, nɑːt ɐn ɛkoʊ!"
    print(text_hat)
    print(len(sequence))
    assert text_hat == text_hat_with_params == gt

    # extra space after the sentence
    text = "Be a voice, not an! echo.  "
    sequence = phoneme_to_sequence(text, text_cleaner, lang)
    text_hat = sequence_to_phoneme(sequence)
    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters, add_blank=True)
    text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters, add_blank=True)
    gt = "biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ."
    print(text_hat)
    print(len(sequence))
    assert text_hat == text_hat_with_params == gt

    # extra space after the sentence
    text = "Be a voice, not an! echo.  "
    sequence = phoneme_to_sequence(text, text_cleaner, lang, True)
    text_hat = sequence_to_phoneme(sequence)
    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters, add_blank=True)
    text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters, add_blank=True)
    gt = "^biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ.~"
    print(text_hat)
    print(len(sequence))
    assert text_hat == text_hat_with_params == gt

    # padding char
    text = "_Be a _voice, not an! echo_"
    sequence = phoneme_to_sequence(text, text_cleaner, lang)
    text_hat = sequence_to_phoneme(sequence)
    _ = phoneme_to_sequence(text, text_cleaner, lang, tp=conf.characters, add_blank=True)
    text_hat_with_params = sequence_to_phoneme(sequence, tp=conf.characters, add_blank=True)
    gt = "biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ"
    print(text_hat)
    print(len(sequence))
    assert text_hat == text_hat_with_params == gt

def test_text2phone():
    text = "Recent research at Harvard has shown meditating for as little as 8 weeks can actually increase, the grey matter in the parts of the brain responsible for emotional regulation and learning!"
    gt = "ɹ|iː|s|ə|n|t| |ɹ|ɪ|s|ɜː|tʃ| |æ|t| |h|ɑːɹ|v|ɚ|d| |h|ɐ|z| |ʃ|oʊ|n| |m|ɛ|d|ᵻ|t|eɪ|ɾ|ɪ|ŋ| |f|ɔː|ɹ| |æ|z| |l|ɪ|ɾ|əl| |æ|z| |eɪ|t| |w|iː|k|s| |k|æ|n| |æ|k|tʃ|uː|əl|i| |ɪ|n|k|ɹ|iː|s|,| |ð|ə| |ɡ|ɹ|eɪ| |m|æ|ɾ|ɚ|ɹ| |ɪ|n|ð|ə| |p|ɑːɹ|t|s| |ʌ|v|ð|ə| |b|ɹ|eɪ|n| |ɹ|ɪ|s|p|ɑː|n|s|ə|b|əl| |f|ɔː|ɹ| |ɪ|m|oʊ|ʃ|ə|n|əl| |ɹ|ɛ|ɡ|j|uː|l|eɪ|ʃ|ə|n| |æ|n|d| |l|ɜː|n|ɪ|ŋ|!"
    lang = "en-us"
    ph = text2phone(text, lang)
    assert gt == ph