SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[Styling] stylify using ruff (#27144)

Browse Source 
* 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
2023-11-16 17:43:19 +01:00
committed by GitHub
parent acb5b4aff5
commit 651408a077
480 changed files with 867 additions and 1059 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
tests/models/speecht5/test_tokenization_speecht5.py
View File

@@ -152,9 +152,7 @@ class SpeechT5TokenizerTest(TokenizerTesterMixin, unittest.TestCase):
tokenizer = self.get_tokenizer(normalize=True)
tokens = tokenizer.tokenize("This is a test")
# fmt: off
self.assertListEqual(tokens, [SPIECE_UNDERLINE, 'T', 'h', 'i', 's', SPIECE_UNDERLINE, 'i', 's', SPIECE_UNDERLINE, 'a', SPIECE_UNDERLINE, 't', 'e', 's', 't'])
# fmt: on
self.assertListEqual(tokens, [SPIECE_UNDERLINE, 'T', 'h', 'i', 's', SPIECE_UNDERLINE, 'i', 's', SPIECE_UNDERLINE, 'a', SPIECE_UNDERLINE, 't', 'e', 's', 't']) # fmt: skip
self.assertListEqual(
tokenizer.convert_tokens_to_ids(tokens),
@@ -162,25 +160,13 @@ class SpeechT5TokenizerTest(TokenizerTesterMixin, unittest.TestCase):
)
tokens = tokenizer.tokenize("I was born in 92000, and this is falsé.")
self.assertListEqual(
tokens,
# fmt: off
[SPIECE_UNDERLINE, 'I', SPIECE_UNDERLINE, 'w', 'a', 's', SPIECE_UNDERLINE, 'b', 'o', 'r', 'n', SPIECE_UNDERLINE, 'i', 'n', SPIECE_UNDERLINE, 'n', 'i', 'n', 'e', 't', 'y', SPIECE_UNDERLINE, 't', 'w', 'o', SPIECE_UNDERLINE, 't', 'h', 'o', 'u', 's', 'a', 'n', 'd', ',', SPIECE_UNDERLINE, 'a', 'n', 'd', SPIECE_UNDERLINE, 't', 'h', 'i', 's', SPIECE_UNDERLINE, 'i', 's', SPIECE_UNDERLINE, 'f', 'a', 'l', 's', 'é', '.']
# fmt: on
)
self.assertListEqual(tokens,[SPIECE_UNDERLINE, 'I', SPIECE_UNDERLINE, 'w', 'a', 's', SPIECE_UNDERLINE, 'b', 'o', 'r', 'n', SPIECE_UNDERLINE, 'i', 'n', SPIECE_UNDERLINE, 'n', 'i', 'n', 'e', 't', 'y', SPIECE_UNDERLINE, 't', 'w', 'o', SPIECE_UNDERLINE, 't', 'h', 'o', 'u', 's', 'a', 'n', 'd', ',', SPIECE_UNDERLINE, 'a', 'n', 'd', SPIECE_UNDERLINE, 't', 'h', 'i', 's', SPIECE_UNDERLINE, 'i', 's', SPIECE_UNDERLINE, 'f', 'a', 'l', 's', 'é', '.']) # fmt: skip
ids = tokenizer.convert_tokens_to_ids(tokens)
# fmt: off
self.assertListEqual(ids, [4, 30, 4, 20, 7, 12, 4, 25, 8, 13, 9, 4, 10, 9, 4, 9, 10, 9, 5, 6, 22, 4, 6, 20, 8, 4, 6, 11, 8, 16, 12, 7, 9, 14, 23, 4, 7, 9, 14, 4, 6, 11, 10, 12, 4, 10, 12, 4, 19, 7, 15, 12, 73, 26])
# fmt: on
self.assertListEqual(ids, [4, 30, 4, 20, 7, 12, 4, 25, 8, 13, 9, 4, 10, 9, 4, 9, 10, 9, 5, 6, 22, 4, 6, 20, 8, 4, 6, 11, 8, 16, 12, 7, 9, 14, 23, 4, 7, 9, 14, 4, 6, 11, 10, 12, 4, 10, 12, 4, 19, 7, 15, 12, 73, 26]) # fmt: skip
back_tokens = tokenizer.convert_ids_to_tokens(ids)
self.assertListEqual(
back_tokens,
# fmt: off
[SPIECE_UNDERLINE, 'I', SPIECE_UNDERLINE, 'w', 'a', 's', SPIECE_UNDERLINE, 'b', 'o', 'r', 'n', SPIECE_UNDERLINE, 'i', 'n', SPIECE_UNDERLINE, 'n', 'i', 'n', 'e', 't', 'y', SPIECE_UNDERLINE, 't', 'w', 'o', SPIECE_UNDERLINE, 't', 'h', 'o', 'u', 's', 'a', 'n', 'd', ',', SPIECE_UNDERLINE, 'a', 'n', 'd', SPIECE_UNDERLINE, 't', 'h', 'i', 's', SPIECE_UNDERLINE, 'i', 's', SPIECE_UNDERLINE, 'f', 'a', 'l', 's', 'é', '.']
# fmt: on
)
self.assertListEqual(back_tokens,[SPIECE_UNDERLINE, 'I', SPIECE_UNDERLINE, 'w', 'a', 's', SPIECE_UNDERLINE, 'b', 'o', 'r', 'n', SPIECE_UNDERLINE, 'i', 'n', SPIECE_UNDERLINE, 'n', 'i', 'n', 'e', 't', 'y', SPIECE_UNDERLINE, 't', 'w', 'o', SPIECE_UNDERLINE, 't', 'h', 'o', 'u', 's', 'a', 'n', 'd', ',', SPIECE_UNDERLINE, 'a', 'n', 'd', SPIECE_UNDERLINE, 't', 'h', 'i', 's', SPIECE_UNDERLINE, 'i', 's', SPIECE_UNDERLINE, 'f', 'a', 'l', 's', 'é', '.']) # fmt: skip
@slow
def test_tokenizer_integration(self):