mirror of
https://github.com/storytold/storyteller-ml.git
synced 2026-10-17 00:23:14 +00:00
Brandon Thomas
76c6dbf12b
This breaks the text pipeline into the following pieces: - input parsing (split known bracketed phoneme sections out first) - normalization (fix spacing, numbers, abbreviations, etc.) - phonetization (do CMUdict lookup or g2p prediction) - sequencing (convert the symbolic representation to integer representation) Each "pipeline" can have a unique combination of operations for each of these pipeline steps. This will grow over time.
16 lines
555 B
Python
16 lines
555 B
Python
from text.pipeline_components.phonetization.cmudict import CMUDict
|
|
from text.pipeline_components.phonetization.cmudict import DEFAULT_CMUDICT_PATH
|
|
|
|
|
|
class TestCmuDict:
|
|
|
|
def test_lookup_success(self):
|
|
cmudict = CMUDict(DEFAULT_CMUDICT_PATH)
|
|
arpabet_sequence = cmudict.lookup('word')
|
|
assert arpabet_sequence == ['W ER1 D'] # TODO: Split the phonemes!
|
|
|
|
def test_lookup_failure(self):
|
|
cmudict = CMUDict(DEFAULT_CMUDICT_PATH)
|
|
arpabet_sequence = cmudict.lookup('fakeword')
|
|
assert arpabet_sequence == None
|