itproject-code

Rob Hallam 251679b89b test: Add functional tests to WordFeatureExtractor (see note) Functional tests for WordFeatureExtractor consist of making sure it can find words known in advance. The Harvard Sentences [1] are a useful means of doing that. These are 'standard sentences' that are used for speech quality measurements, and so would be decent candidates for assessing word recognition. The Open Speech REpository [2] has samples of sentences to download. In testing, the Whisper medium model had trouble with a few words: - glue - well - punch - truck I'm not sure why. Even when I recorded myself speaking the Harvard sentences in higher quality (OSR files are 8kHz range) it would still not recognise these words. A separate functional test of only those words was added as a result. This would perhaps be worth exploring in more detail if there was time. [1]: See eg https://www.cs.columbia.edu/~hgs/audio/harvard.html [2]: https://www.voiptroubleshooter.com/open_speech/index.html		2 个月前
..
__init__.py	feat: add __init__, TestOverlapConsolidation suite	3 个月前
context.py	feat: add context to ease testing	3 个月前
mocks.py	test: [mocks] add attrs to MockFeature + MockSource.duration()	3 个月前
test_consolidate.py	test: add move_end method for overlap testing	3 个月前
test_feature_extractors.py	test: [WFE] Negative and aprtial tests	2 个月前
test_feature_extractors_functional.py	test: Add functional tests to WordFeatureExtractor (see note)	2 个月前
test_producers.py	refactor!: rename video_producers → producers	3 个月前
test_utils.py	test: [utils] add TestFeature fixtures	3 个月前