def test_encode_batch_with_example_with_empty_first_elem():
features = Features({
"x": Sequence(Sequence(ClassLabel(names=["a", "b"]))),
})
encoded_batch = features.encode_batch(
{"x": [
[["a"], ["b"]],
[[], ["b"]],
]})
assert encoded_batch == {"x": [[[0], [1]], [[], [1]]]}
def test_dataset_with_audio_feature_map_is_not_decoded(shared_datadir):
audio_path = str(shared_datadir / "test_audio_44100.wav")
data = {"audio": [audio_path], "text": ["Hello"]}
features = Features({"audio": Audio(), "text": Value("string")})
dset = Dataset.from_dict(data, features=features)
expected_audio = features.encode_batch(data)["audio"][0]
for item in dset._iter(decoded=False):
assert item.keys() == {"audio", "text"}
assert item == {"audio": expected_audio, "text": "Hello"}
def process_text(example):
example["text"] = example["text"] + " World!"
return example
processed_dset = dset.map(process_text)
for item in processed_dset._iter(decoded=False):
assert item.keys() == {"audio", "text"}
assert item == {"audio": expected_audio, "text": "Hello World!"}
