def test_split_by_length_of_utterances(benchmark):
corpus = resources.generate_corpus(179, (250, 500), (1, 9), (0, 6),
(1, 20), random.Random(x=234))
splitter = subset.Splitter(corpus, random_seed=324)
benchmark(run, splitter)
def test_subview(benchmark):
corpus = resources.generate_corpus(200, (5, 10), (1, 5), (0, 6), (1, 20),
random.Random(x=234))
random.seed(200)
filtered_utts = random.choices(list(corpus.utterances.keys()), k=20000)
filters = [subset.MatchingUtteranceIdxFilter(filtered_utts)]
benchmark(run, corpus, filters)
def test_kaldi_write(benchmark, tmp_path):
corpus = resources.generate_corpus(
200,
(5, 10),
(1, 5),
(0, 6),
(1, 20),
random.Random(x=234)
)
benchmark(run, corpus, str(tmp_path))
def test_from_corpus(benchmark):
source_corpus = resources.generate_corpus(
200,
(5, 5),
(5, 5),
(4, 4),
(4, 4),
random.Random(x=234)
)
benchmark(run, source_corpus)
from bench import resources
def run(source_corpus):
audiomate.Corpus.from_corpus(source_corpus)
def test_from_corpus(benchmark):
source_corpus = resources.generate_corpus(
200,
(5, 5),
(5, 5),
(4, 4),
(4, 4),
random.Random(x=234)
)
benchmark(run, source_corpus)
if __name__ == '__main__':
source_corpus = resources.generate_corpus(
200,
(5, 10),
(1, 5),
(0, 6),
(1, 20),
random.Random(x=234)
)
audiomate.Corpus.from_corpus(source_corpus)
def test_merge_corpus(benchmark):
target_corpus = audiomate.Corpus()
merge_corpus = resources.generate_corpus(200, (5, 10), (1, 5), (0, 6),
(1, 20), random.Random(x=234))
benchmark(run, target_corpus, merge_corpus)