[Styling] stylify using ruff (#27144)
* try to stylify using ruff * might need to remove these changes? * use ruf format andruff check * use isinstance instead of type comparision * use # fmt: skip * use # fmt: skip * nits * soem styling changes * update ci job * nits isinstance * more files update * nits * more nits * small nits * check and format * revert wrong changes * actually use formatter instead of checker * nits * well docbuilder is overwriting this commit * revert notebook changes * try to nuke docbuilder * style * fix feature exrtaction test * remve `indent-width = 4` * fixup * more nits * update the ruff version that we use * style * nuke docbuilder styling * leve the print for detected changes * nits * Remove file I/O Co-authored-by: charliermarsh <charlie.r.marsh@gmail.com> * style * nits * revert notebook changes * Add # fmt skip when possible * Add # fmt skip when possible * Fix * More ` # fmt: skip` usage * More ` # fmt: skip` usage * More ` # fmt: skip` usage * NIts * more fixes * fix tapas * Another way to skip * Recommended way * Fix two more fiels * Remove asynch Remove asynch --------- Co-authored-by: charliermarsh <charlie.r.marsh@gmail.com>
This commit is contained in:
Arthur
@@ -77,20 +77,16 @@ class WhisperTokenizerTest(TokenizerTesterMixin, unittest.TestCase):
|
||||
tokens = tokenizer.tokenize("I was born in 92000, and this is falsé.")
|
||||
self.assertListEqual(
|
||||
tokens,
|
||||
# fmt: off
|
||||
['I', 'Ġwas', 'Ġborn', 'Ġin', 'Ġ9', '2000', ',', 'Ġand', 'Ġ', 'this', 'Ġis', 'Ġfals', 'é', '.'],
|
||||
# fmt: on
|
||||
)
|
||||
["I", "Ġwas", "Ġborn", "Ġin", "Ġ9", "2000", ",", "Ġand", "Ġ", "this", "Ġis", "Ġfals", "é", "."], # fmt: skip
|
||||
) # fmt: skip
|
||||
ids = tokenizer.convert_tokens_to_ids(tokens)
|
||||
self.assertListEqual(ids, [40, 390, 4232, 294, 1722, 25743, 11, 293, 220, 11176, 307, 16720, 526, 13])
|
||||
|
||||
back_tokens = tokenizer.convert_ids_to_tokens(ids)
|
||||
self.assertListEqual(
|
||||
back_tokens,
|
||||
# fmt: off
|
||||
['I', 'Ġwas', 'Ġborn', 'Ġin', 'Ġ9', '2000', ',', 'Ġand', 'Ġ', 'this', 'Ġis', 'Ġfals', 'é', '.'],
|
||||
# fmt: on
|
||||
)
|
||||
["I", "Ġwas", "Ġborn", "Ġin", "Ġ9", "2000", ",", "Ġand", "Ġ", "this", "Ġis", "Ġfals", "é", "."], # fmt: skip
|
||||
) # fmt: skip
|
||||
|
||||
def test_tokenizer_slow_store_full_signature(self):
|
||||
pass
|
||||
@@ -108,9 +104,7 @@ class WhisperTokenizerTest(TokenizerTesterMixin, unittest.TestCase):
|
||||
|
||||
@slow
|
||||
def test_tokenizer_integration(self):
|
||||
# fmt: off
|
||||
expected_encoding = {'input_ids': [[50257, 50362, 41762, 364, 357, 36234, 1900, 355, 12972, 13165, 354, 12, 35636, 364, 290, 12972, 13165, 354, 12, 5310, 13363, 12, 4835, 8, 3769, 2276, 12, 29983, 45619, 357, 13246, 51, 11, 402, 11571, 12, 17, 11, 5564, 13246, 38586, 11, 16276, 44, 11, 4307, 346, 33, 861, 11, 16276, 7934, 23029, 329, 12068, 15417, 28491, 357, 32572, 52, 8, 290, 12068, 15417, 16588, 357, 32572, 38, 8, 351, 625, 3933, 10, 2181, 13363, 4981, 287, 1802, 10, 8950, 290, 2769, 48817, 1799, 1022, 449, 897, 11, 9485, 15884, 354, 290, 309, 22854, 37535, 13, 50256], [50257, 50362, 13246, 51, 318, 3562, 284, 662, 12, 27432, 2769, 8406, 4154, 282, 24612, 422, 9642, 9608, 276, 2420, 416, 26913, 21143, 319, 1111, 1364, 290, 826, 4732, 287, 477, 11685, 13, 50256], [50257, 50362, 464, 2068, 7586, 21831, 18045, 625, 262, 16931, 3290, 13, 50256]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]} # noqa: E501
|
||||
# fmt: on
|
||||
expected_encoding = {'input_ids': [[50257, 50362, 41762, 364, 357, 36234, 1900, 355, 12972, 13165, 354, 12, 35636, 364, 290, 12972, 13165, 354, 12, 5310, 13363, 12, 4835, 8, 3769, 2276, 12, 29983, 45619, 357, 13246, 51, 11, 402, 11571, 12, 17, 11, 5564, 13246, 38586, 11, 16276, 44, 11, 4307, 346, 33, 861, 11, 16276, 7934, 23029, 329, 12068, 15417, 28491, 357, 32572, 52, 8, 290, 12068, 15417, 16588, 357, 32572, 38, 8, 351, 625, 3933, 10, 2181, 13363, 4981, 287, 1802, 10, 8950, 290, 2769, 48817, 1799, 1022, 449, 897, 11, 9485, 15884, 354, 290, 309, 22854, 37535, 13, 50256], [50257, 50362, 13246, 51, 318, 3562, 284, 662, 12, 27432, 2769, 8406, 4154, 282, 24612, 422, 9642, 9608, 276, 2420, 416, 26913, 21143, 319, 1111, 1364, 290, 826, 4732, 287, 477, 11685, 13, 50256], [50257, 50362, 464, 2068, 7586, 21831, 18045, 625, 262, 16931, 3290, 13, 50256]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]} # fmt: skip
|
||||
|
||||
self.tokenizer_integration_test_util(
|
||||
expected_encoding=expected_encoding, model_name="openai/whisper-tiny.en", padding=False
|
||||
@@ -128,9 +122,7 @@ class WhisperTokenizerTest(TokenizerTesterMixin, unittest.TestCase):
|
||||
)
|
||||
|
||||
# Merge when the previous sequence is a suffix of the next sequence
|
||||
# fmt: off
|
||||
next_sequences_1 = [50364, 295, 6177, 3391, 11, 19817, 3337, 507, 307, 406, 3163, 1953, 466, 13, 50614, 50614, 2812, 9836, 14783, 390, 6263, 538, 257, 1359, 11, 8199, 6327, 1090, 322, 702, 7443, 13, 50834, 50257]
|
||||
# fmt: on
|
||||
next_sequences_1 = [50364, 295, 6177, 3391, 11, 19817, 3337, 507, 307, 406, 3163, 1953, 466, 13, 50614, 50614, 2812, 9836, 14783, 390, 6263, 538, 257, 1359, 11, 8199, 6327, 1090, 322, 702, 7443, 13, 50834, 50257] # fmt: skip
|
||||
self.assertEqual(
|
||||
tokenizer.decode(next_sequences_1, output_offsets=True),
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user