Skip to content

Commit 44e43dd

Browse files
ekmbekmb
authored
fix sv tests (#52)
Signed-off-by: ekmb <ebakhturina@nvidia.com>
1 parent 2db73f5 commit 44e43dd

14 files changed

Lines changed: 72 additions & 43 deletions

‎Jenkinsfile‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ pipeline {
1919
PT_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/02-15-23-0'
2020
RU_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/02-15-23-0'
2121
VI_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/02-15-23-0'
22-
SV_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/02-16-23-0'
22+
SV_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/03-09-23-0'
2323
ZH_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/02-15-23-0'
2424
DEFAULT_TN_CACHE='/home/jenkinsci/TestData/text_norm/ci/grammars/02-15-23-0'
2525

‎tests/nemo_text_processing/sv/test_cardinal.py‎

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -17,14 +17,16 @@
1717
from nemo_text_processing.text_normalization.normalize_with_audio import NormalizerWithAudio
1818
from parameterized import parameterized
1919

20-
from ..utils import CACHE_DIR, parse_test_case_file
20+
from ..utils import CACHE_DIR, RUN_AUDIO_BASED_TESTS, parse_test_case_file
2121

2222

2323
class TestCardinal:
2424
normalizer = Normalizer(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
2525

26-
normalizer_with_audio = NormalizerWithAudio(
27-
input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False
26+
normalizer_with_audio = (
27+
NormalizerWithAudio(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
28+
if RUN_AUDIO_BASED_TESTS
29+
else None
2830
)
2931

3032
@parameterized.expand(parse_test_case_file('sv/data_text_normalization/test_cases_cardinal.txt'))

‎tests/nemo_text_processing/sv/test_date.py‎

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -17,14 +17,16 @@
1717
from nemo_text_processing.text_normalization.normalize_with_audio import NormalizerWithAudio
1818
from parameterized import parameterized
1919

20-
from ..utils import CACHE_DIR, parse_test_case_file
20+
from ..utils import CACHE_DIR, RUN_AUDIO_BASED_TESTS, parse_test_case_file
2121

2222

2323
class TestDate:
2424
normalizer = Normalizer(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
2525

26-
normalizer_with_audio = NormalizerWithAudio(
27-
input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False
26+
normalizer_with_audio = (
27+
NormalizerWithAudio(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
28+
if RUN_AUDIO_BASED_TESTS
29+
else None
2830
)
2931

3032
@parameterized.expand(parse_test_case_file('sv/data_text_normalization/test_cases_date.txt'))

‎tests/nemo_text_processing/sv/test_decimal.py‎

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -17,14 +17,16 @@
1717
from nemo_text_processing.text_normalization.normalize_with_audio import NormalizerWithAudio
1818
from parameterized import parameterized
1919

20-
from ..utils import CACHE_DIR, parse_test_case_file
20+
from ..utils import CACHE_DIR, RUN_AUDIO_BASED_TESTS, parse_test_case_file
2121

2222

2323
class TestDecimal:
2424
normalizer = Normalizer(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
2525

26-
normalizer_with_audio = NormalizerWithAudio(
27-
input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False
26+
normalizer_with_audio = (
27+
NormalizerWithAudio(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
28+
if RUN_AUDIO_BASED_TESTS
29+
else None
2830
)
2931

3032
@parameterized.expand(parse_test_case_file('sv/data_text_normalization/test_cases_decimal.txt'))

‎tests/nemo_text_processing/sv/test_electronic.py‎

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -17,14 +17,16 @@
1717
from nemo_text_processing.text_normalization.normalize_with_audio import NormalizerWithAudio
1818
from parameterized import parameterized
1919

20-
from ..utils import CACHE_DIR, parse_test_case_file
20+
from ..utils import CACHE_DIR, RUN_AUDIO_BASED_TESTS, parse_test_case_file
2121

2222

2323
class TestElectronic:
2424
normalizer = Normalizer(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
2525

26-
normalizer_with_audio = NormalizerWithAudio(
27-
input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False
26+
normalizer_with_audio = (
27+
NormalizerWithAudio(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
28+
if RUN_AUDIO_BASED_TESTS
29+
else None
2830
)
2931

3032
@parameterized.expand(parse_test_case_file('sv/data_text_normalization/test_cases_electronic.txt'))

‎tests/nemo_text_processing/sv/test_fraction.py‎

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -18,14 +18,16 @@
1818
from nemo_text_processing.text_normalization.normalize_with_audio import NormalizerWithAudio
1919
from parameterized import parameterized
2020

21-
from ..utils import CACHE_DIR, parse_test_case_file
21+
from ..utils import CACHE_DIR, RUN_AUDIO_BASED_TESTS, parse_test_case_file
2222

2323

2424
class TestFraction:
2525
normalizer = Normalizer(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
2626

27-
normalizer_with_audio = NormalizerWithAudio(
28-
input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False
27+
normalizer_with_audio = (
28+
NormalizerWithAudio(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
29+
if RUN_AUDIO_BASED_TESTS
30+
else None
2931
)
3032

3133
@parameterized.expand(parse_test_case_file('sv/data_text_normalization/test_cases_fraction.txt'))

‎tests/nemo_text_processing/sv/test_measure.py‎

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -18,14 +18,16 @@
1818
from nemo_text_processing.text_normalization.normalize_with_audio import NormalizerWithAudio
1919
from parameterized import parameterized
2020

21-
from ..utils import CACHE_DIR, parse_test_case_file
21+
from ..utils import CACHE_DIR, RUN_AUDIO_BASED_TESTS, parse_test_case_file
2222

2323

2424
class TestMeasure:
2525
normalizer = Normalizer(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
2626

27-
normalizer_with_audio = NormalizerWithAudio(
28-
input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False
27+
normalizer_with_audio = (
28+
NormalizerWithAudio(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
29+
if RUN_AUDIO_BASED_TESTS
30+
else None
2931
)
3032

3133
@parameterized.expand(parse_test_case_file('sv/data_text_normalization/test_cases_measure.txt'))

‎tests/nemo_text_processing/sv/test_money.py‎

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -18,14 +18,16 @@
1818
from nemo_text_processing.text_normalization.normalize_with_audio import NormalizerWithAudio
1919
from parameterized import parameterized
2020

21-
from ..utils import CACHE_DIR, parse_test_case_file
21+
from ..utils import CACHE_DIR, RUN_AUDIO_BASED_TESTS, parse_test_case_file
2222

2323

2424
class TestMoney:
2525
normalizer = Normalizer(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
2626

27-
normalizer_with_audio = NormalizerWithAudio(
28-
input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False
27+
normalizer_with_audio = (
28+
NormalizerWithAudio(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
29+
if RUN_AUDIO_BASED_TESTS
30+
else None
2931
)
3032

3133
@parameterized.expand(parse_test_case_file('sv/data_text_normalization/test_cases_money.txt'))

‎tests/nemo_text_processing/sv/test_normalization_with_audio.py‎

Lines changed: 11 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -16,17 +16,22 @@
1616
from nemo_text_processing.text_normalization.normalize_with_audio import NormalizerWithAudio
1717
from parameterized import parameterized
1818

19-
from ..utils import CACHE_DIR, get_test_cases_multiple
19+
from ..utils import CACHE_DIR, RUN_AUDIO_BASED_TESTS, get_test_cases_multiple
2020

2121

2222
class TestNormalizeWithAudio:
23-
normalizer = NormalizerWithAudio(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
23+
normalizer_with_audio = (
24+
NormalizerWithAudio(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
25+
if RUN_AUDIO_BASED_TESTS
26+
else None
27+
)
2428

2529
@parameterized.expand(get_test_cases_multiple('sv/data_text_normalization/test_cases_normalize_with_audio.txt'))
2630
@pytest.mark.run_only_on('CPU')
2731
@pytest.mark.unit
2832
def test_norm(self, test_input, expected):
29-
pred = self.normalizer.normalize(test_input, n_tagged=150, punct_post_process=False)
30-
assert len(set(pred).intersection(set(expected))) == len(
31-
expected
32-
), f'missing: {set(expected).difference(set(pred))}'
33+
if self.normalizer_with_audio:
34+
pred = self.normalizer_with_audio.normalize(test_input, n_tagged=150, punct_post_process=False)
35+
assert len(set(pred).intersection(set(expected))) == len(
36+
expected
37+
), f'missing: {set(expected).difference(set(pred))}'

‎tests/nemo_text_processing/sv/test_ordinal.py‎

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -18,14 +18,16 @@
1818
from nemo_text_processing.text_normalization.normalize_with_audio import NormalizerWithAudio
1919
from parameterized import parameterized
2020

21-
from ..utils import CACHE_DIR, parse_test_case_file
21+
from ..utils import CACHE_DIR, RUN_AUDIO_BASED_TESTS, parse_test_case_file
2222

2323

2424
class TestOrdinal:
2525
normalizer = Normalizer(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
2626

27-
normalizer_with_audio = NormalizerWithAudio(
28-
input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False
27+
normalizer_with_audio = (
28+
NormalizerWithAudio(input_case='cased', lang='sv', cache_dir=CACHE_DIR, overwrite_cache=False)
29+
if RUN_AUDIO_BASED_TESTS
30+
else None
2931
)
3032

3133
@parameterized.expand(parse_test_case_file('sv/data_text_normalization/test_cases_ordinal.txt'))

0 commit comments

Comments
 (0)