wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-10 11:50:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

text processing updates with tests

Browse Source
This commit is contained in:
Eren Golge
2019-03-29 17:04:10 +01:00
parent e1573440ba
commit 103971c893
3 changed files with 50 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/text_processing_tests.py
+37 -1
View File
@@ -12,6 +12,42 @@ def test_phoneme_to_sequence():
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 == gt
# multiple punctuations
text = "Be a voice, not an! echo?"
sequence = phoneme_to_sequence(text, text_cleaner, lang)
text_hat = sequence_to_phoneme(sequence)
gt = "^biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ?"
print(text_hat)
print(len(sequence))
assert text_hat == 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)
gt = "^biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ"
print(text_hat)
print(len(sequence))
assert text_hat == gt
# original
text = "Be a voice, not an echo!"
sequence = phoneme_to_sequence(text, text_cleaner, lang)
text_hat = sequence_to_phoneme(sequence)
gt = "^biː ɐ vɔɪs, nɑːt ɐn ɛkoʊ!"
print(text_hat)
print(len(sequence))
assert text_hat == 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)
gt = "^biː ɐ vɔɪs, nɑːt ɐn! ɛkoʊ."
print(text_hat)
print(len(sequence))
assert text_hat == 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!"
@@ -19,4 +55,4 @@ def test_text2phone():
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"
phonemes = text2phone(text, lang)
assert gt == phonemes
assert gt == phonemes