wehub-resource-sync
ba4be087d5
Create PR to main with cherry-pick from release / cherry-pick (push) Failing after 0s
CICD NeMo / pre-flight (push) Failing after 0s
CICD NeMo / configure (push) Has been skipped
Build, validate, and release Neural Modules / pre-flight (push) Failing after 1s
CICD NeMo / code-linting (push) Has been skipped
Build, validate, and release Neural Modules / release (push) Has been skipped
Build, validate, and release Neural Modules / release-summary (push) Has been cancelled
CICD NeMo / cicd-test-container-build (push) Has been cancelled
CICD NeMo / cicd-import-tests (push) Has been cancelled
CICD NeMo / L0_Setup_Test_Data_And_Models (push) Has been cancelled
CICD NeMo / cicd-main-unit-tests (push) Has been cancelled
CICD NeMo / cicd-main-speech (push) Has been cancelled
CICD NeMo / Nemo_CICD_Test (push) Has been cancelled
CICD NeMo / Coverage (e2e) (push) Has been cancelled
CICD NeMo / Coverage (unit-test) (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled
CICD NeMo / cicd-wait-in-queue (push) Has been cancelled
57 lines
2.3 KiB
Python
57 lines
2.3 KiB
Python
# Copyright (c) 2025, NVIDIA CORPORATION. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
|
|
import pytest
|
|
|
|
from nemo.collections.asr.inference.utils.text_segment import TextSegment, Word, join_segments
|
|
|
|
|
|
class TestTextSegment:
|
|
|
|
@pytest.mark.unit
|
|
@pytest.mark.parametrize("text, expected_text", [("Hello!", "hello"), ("HeLLo!", "hello")])
|
|
def test_normalize_text_inplace(self, text, expected_text):
|
|
for cls in [Word, TextSegment]:
|
|
text_segment = cls(text, 0, 1, 0.5)
|
|
text_segment.normalize_text_inplace(punct_marks='!', sep=' ')
|
|
assert text_segment.text == expected_text
|
|
|
|
@pytest.mark.unit
|
|
@pytest.mark.parametrize("text, expected_text", [("Hello!", "hello"), ("HeLLo!", "hello")])
|
|
def test_with_normalized_text(self, text, expected_text):
|
|
for cls in [Word, TextSegment]:
|
|
text_segment = cls(text, 0, 1, 0.5)
|
|
text_segment_copy = text_segment.with_normalized_text(punct_marks='!', sep=' ')
|
|
assert text_segment_copy.text == expected_text
|
|
assert text_segment.text == text
|
|
|
|
@pytest.mark.unit
|
|
def test_join_segments(self):
|
|
for cls in [Word, TextSegment]:
|
|
segments = [
|
|
[cls('hello', 0, 1, 0.5), cls('world', 1, 2, 0.5)],
|
|
[cls('how', 2, 3, 0.5), cls('are', 3, 4, 0.5), cls('you', 4, 5, 0.5)],
|
|
]
|
|
transcriptions = join_segments(segments, sep=' ')
|
|
assert transcriptions == ['hello world', 'how are you']
|
|
|
|
@pytest.mark.unit
|
|
@pytest.mark.parametrize("text, expected_text", [("hello", "Hello"), ("World!", "World!")])
|
|
def test_capitalize(self, text, expected_text):
|
|
for cls in [Word, TextSegment]:
|
|
text_segment = cls(text, 0, 1, 0.5)
|
|
text_segment.capitalize()
|
|
assert text_segment.text == expected_text
|