Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

update test_text_processing for espeak-ng

This commit is contained in:
Eren Gölge 2021-02-12 14:07:26 +00:00
parent b28c724c04
commit 4244096ccb
2 changed files with 15 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
TTS/tts/utils/text/__init__.py
View File

@ -24,7 +24,7 @@ _phonemes = phonemes
_CURLY_RE = re.compile(r'(.*?)\{(.+?)\}(.*)')
# Regular expression matching punctuations, ignoring empty space
PHONEME_PUNCTUATION_PATTERN = r'['+_punctuations+']+'
PHONEME_PUNCTUATION_PATTERN = r'['+_punctuations.replace(' ', '')+']+'
def text2phone(text, language):

28
tests/test_text_processing.py
View File

@ -19,7 +19,7 @@ def test_phoneme_to_sequence():
text_hat = sequence_to_phoneme(sequence)
sequence_with_params = 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!"
gt = 'ɹiːsənt ɹᵻsɜːtʃ æt hɑːɹvɚd hɐz ʃoʊn mɛdᵻteɪɾɪŋ fɔːɹ æz lɪɾəl æz eɪt wiːks kæn æktʃuːəli ɪŋkɹiːs, ðə ɡɹeɪ mæɾɚɹ ɪnðə pɑːɹts ʌvðə bɹeɪn ɹᵻspɑːnsᵻbəl fɔːɹ ɪmoʊʃənəl ɹɛɡjʊleɪʃən ænd lɜːnɪŋ!'
assert text_hat == text_hat_with_params == gt
# multiple punctuations
@ -28,7 +28,7 @@ def test_phoneme_to_sequence():
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?"
gt = "biː ɐ vɔɪs, nɑːt æn! ɛkoʊ?"
print(text_hat)
print(len(sequence))
assert text_hat == text_hat_with_params == gt
@ -39,7 +39,7 @@ def test_phoneme_to_sequence():
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"
gt = "biː ɐ vɔɪs, nɑːt æn! ɛkoʊ"
print(text_hat)
print(len(sequence))
assert text_hat == text_hat_with_params == gt
@ -61,7 +61,7 @@ def test_phoneme_to_sequence():
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."
gt = "biː ɐ vɔɪs, nɑːt æn! ɛkoʊ."
print(text_hat)
print(len(sequence))
assert text_hat == text_hat_with_params == gt
@ -72,7 +72,7 @@ def test_phoneme_to_sequence():
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.~"
gt = "^biː ɐ vɔɪs, nɑːt æn! ɛkoʊ.~"
print(text_hat)
print(len(sequence))
assert text_hat == text_hat_with_params == gt
@ -83,7 +83,7 @@ def test_phoneme_to_sequence():
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"
gt = "biː ɐ vɔɪs, nɑːt æn! ɛkoʊ"
print(text_hat)
print(len(sequence))
assert text_hat == text_hat_with_params == gt
@ -97,7 +97,7 @@ def test_phoneme_to_sequence_with_blank_token():
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!"
gt = "ɹiːsənt ɹᵻsɜːtʃ æt hɑːɹvɚd hɐz ʃoʊn mɛdᵻteɪɾɪŋ fɔːɹ æz lɪɾəl æz eɪt wiːks kæn æktʃuːəli ɪŋkɹiːs, ðə ɡɹeɪ mæɾɚɹ ɪnðə pɑːɹts ʌvðə bɹeɪn ɹᵻspɑːnsᵻbəl fɔːɹ ɪmoʊʃənəl ɹɛɡjʊleɪʃən ænd lɜːnɪŋ!"
assert text_hat == text_hat_with_params == gt
# multiple punctuations
@ -106,7 +106,7 @@ def test_phoneme_to_sequence_with_blank_token():
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?"
gt = 'biː ɐ vɔɪs, nɑːt æn! ɛkoʊ?'
print(text_hat)
print(len(sequence))
assert text_hat == text_hat_with_params == gt
@ -117,7 +117,7 @@ def test_phoneme_to_sequence_with_blank_token():
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"
gt = 'biː ɐ vɔɪs, nɑːt æn! ɛkoʊ'
print(text_hat)
print(len(sequence))
assert text_hat == text_hat_with_params == gt
@ -128,7 +128,7 @@ def test_phoneme_to_sequence_with_blank_token():
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!"
gt = 'biː ɐ vɔɪs, nɑːt ɐn ɛkoʊ!'
print(text_hat)
print(len(sequence))
assert text_hat == text_hat_with_params == gt
@ -139,7 +139,7 @@ def test_phoneme_to_sequence_with_blank_token():
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."
gt = 'biː ɐ vɔɪs, nɑːt æn! ɛkoʊ.'
print(text_hat)
print(len(sequence))
assert text_hat == text_hat_with_params == gt
@ -150,7 +150,7 @@ def test_phoneme_to_sequence_with_blank_token():
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.~"
gt = "^biː ɐ vɔɪs, nɑːt æn! ɛkoʊ.~"
print(text_hat)
print(len(sequence))
assert text_hat == text_hat_with_params == gt
@ -161,14 +161,14 @@ def test_phoneme_to_sequence_with_blank_token():
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"
gt = "biː ɐ vɔɪs, nɑːt æn! 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|!"
gt = 'ɹ|iː|s|ə|n|t| |ɹ|ᵻ|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|ŋ|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|ᵻ|s|p|ɑː|n|s|ᵻ|b|əl| |f|ɔː|ɹ| |ɪ|m|oʊ|ʃ|ə|n|əl| |ɹ|ɛ|ɡ|j|ʊ|l|eɪ|ʃ|ə|n| |æ|n|d| |l|ɜː|n|ɪ|ŋ|!'
lang = "en-us"
ph = text2phone(text, lang)
assert gt == ph