storytold/storyteller-ml
2
0
Fork 0
mirror of https://github.com/storytold/storyteller-ml.git synced 2026-10-28 09:08:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix tests

Browse Source
This commit is contained in:
Brandon Thomas
2022-07-04 00:48:55 -04:00
parent 7529181864
commit c5ae491895
2 changed files with 51 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tts/text/phonetization/test_english_phonetization.py
+46 -5
View File
@@ -1,5 +1,7 @@
from tts.text.phonetization.cmudict import DEFAULT_CMUDICT_PATH, CMUDict
from tts.text.phonetization.english_phonetization import EnglishPhonetization
from tts.text.input_parsing.parser import ArpabetSequence
from tts.text.input_parsing.parser import GraphemeSequence
class TestEnglishPhonetization:
@@ -13,20 +15,59 @@ class TestEnglishPhonetization:
phoneme_dictionary = CMUDict(DEFAULT_CMUDICT_PATH)
phonetization = EnglishPhonetization(phoneme_dictionary)
output = phonetization.try_convert_to_phonemes("this is a test")
assert output == ["DH IH1 S", "IH1 Z", "AH0", "T EH1 S T"]
assert output == [
ArpabetSequence("DH IH1 S"),
ArpabetSequence("IH1 Z"),
ArpabetSequence("AH0"),
ArpabetSequence("T EH1 S T"),
]
def test_most_words_in_dictionary(self):
phoneme_dictionary = CMUDict(DEFAULT_CMUDICT_PATH)
phonetization = EnglishPhonetization(phoneme_dictionary)
output = phonetization.try_convert_to_phonemes("nonword is a test")
assert output == ["nonword", "IH1 Z", "AH0", "T EH1 S T"]
assert output == [
GraphemeSequence("nonword"),
ArpabetSequence("IH1 Z"),
ArpabetSequence("AH0"),
ArpabetSequence("T EH1 S T"),
]
def test_punctuation(self):
phoneme_dictionary = CMUDict(DEFAULT_CMUDICT_PATH)
phonetization = EnglishPhonetization(phoneme_dictionary)
output = phonetization.try_convert_to_phonemes("this...")
assert output == ["DH IH1 S", "..."]
assert output == [
ArpabetSequence("DH IH1 S"),
GraphemeSequence("..."),
]
output = phonetization.try_convert_to_phonemes("this!")
assert output == ["DH IH1 S", "!"]
assert output == [
ArpabetSequence("DH IH1 S"),
GraphemeSequence("!"),
]
output = phonetization.try_convert_to_phonemes("this?")
assert output == ["DH IH1 S", "?"]
assert output == [
ArpabetSequence("DH IH1 S"),
GraphemeSequence("?"),
]
def test_extra_spaces(self):
phoneme_dictionary = CMUDict(DEFAULT_CMUDICT_PATH)
phonetization = EnglishPhonetization(phoneme_dictionary)
output = phonetization.try_convert_to_phonemes(" this is a test ")
assert output == [
ArpabetSequence("DH IH1 S"),
ArpabetSequence("IH1 Z"),
ArpabetSequence("AH0"),
ArpabetSequence("T EH1 S T"),
]
def test_multi_non_word_extra_spaces(self):
phoneme_dictionary = CMUDict(DEFAULT_CMUDICT_PATH)
phonetization = EnglishPhonetization(phoneme_dictionary)
output = phonetization.try_convert_to_phonemes(" nonword anothernonword ")
assert output == [
GraphemeSequence("nonword"),
GraphemeSequence("anothernonword"),
]