mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-05 22:00:09 +06:00
37ed3ab719
* improve slow class tok usage at xlm rob * add subword regularization for barthez * improve barthez tok. test * fix tokenizer tests * add subword regularization for camembert * add subword regularization for deberta v2 tokenizer * add more doc to deberta v2 tokenizer * add subword regularization for speech to text tok. * fix sp_model_kwargs type in speech 2 text tok. * add subword regularization for M2M100 tok. * add more concrete type hints * fix tests for m2m100 and s2t tok. * add missing Any import * fix syntax error in m2m100 tok. * fix unpickle of m2m100 and s2t tok. * fix test of m2m100 and s2t tok. * improve unpickle of deberta v2 tok. * add test for pickle of barthez & camembert * fix pickle of barthez & camembert * add test for deberta v2 tok. pickle * fix m2m100 tok. pickle * fix s2t tok. pickle * add subword regularization to albert tok. * refactor subword reg. test into TokenizerTesterMixin improve albert tok. test remove sample argument form albert tok. check subword reg. using TokenizerTesterMixin improve tok. tests improve xlm roberta tok. tests improve xlm roberta tok. tests * add subword regularization for big bird t. * improve xlm roberta tok. test * add subword regularization for mbart50 tok. * add subword regularization for pegasus tok. * add subword regularization for reformer tok. * add subword regularization for T5 tok. * fix t5 tok. test formatting * add subword regularization for xlm_proph. tok. * add subword regularization for xlnet tok. * add subword regularization for gert_gen tok. * add typing to tokenizers * add typing to xlm rob. tok * add subword regularization for marian tok. * add reverse tok. test * fix marian tok test * fix marian tok test * fix casing in tok. tests * fix style of tok. common test * fix deberta v2 tok test * add type annotations to tok. tests * add type annotations to tok. __init__ * add typing to kokenizer * add type annotations to tok. __init__ * don't specify the default when it's None * fix barthez tok. doc * move sentencepiece tok. tests to TokenizerTesterMixin * fix unused imports * fix albert tok. test * add comment to sentencepiece test options * fix Any import at big bird tok. * fix Any import at xlm prophetnet tok. * empty commit to trigger CI
153 lines
7.5 KiB
Python
153 lines
7.5 KiB
Python
# coding=utf-8
|
|
# Copyright 2019 Hugging Face inc.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import os
|
|
import unittest
|
|
|
|
from transformers import AlbertTokenizer, AlbertTokenizerFast
|
|
from transformers.testing_utils import require_sentencepiece, require_tokenizers, slow
|
|
|
|
from .test_tokenization_common import TokenizerTesterMixin
|
|
|
|
|
|
SAMPLE_VOCAB = os.path.join(os.path.dirname(os.path.abspath(__file__)), "fixtures/spiece.model")
|
|
|
|
|
|
@require_sentencepiece
|
|
@require_tokenizers
|
|
class AlbertTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
|
|
|
|
tokenizer_class = AlbertTokenizer
|
|
rust_tokenizer_class = AlbertTokenizerFast
|
|
test_rust_tokenizer = True
|
|
test_sentencepiece = True
|
|
test_sentencepiece_ignore_case = True
|
|
|
|
def setUp(self):
|
|
super().setUp()
|
|
|
|
# We have a SentencePiece fixture for testing
|
|
tokenizer = AlbertTokenizer(SAMPLE_VOCAB)
|
|
tokenizer.save_pretrained(self.tmpdirname)
|
|
|
|
def get_input_output_texts(self, tokenizer):
|
|
input_text = "this is a test"
|
|
output_text = "this is a test"
|
|
return input_text, output_text
|
|
|
|
def test_rust_and_python_full_tokenizers(self):
|
|
if not self.test_rust_tokenizer:
|
|
return
|
|
|
|
tokenizer = self.get_tokenizer()
|
|
rust_tokenizer = self.get_rust_tokenizer()
|
|
|
|
sequence = "I was born in 92000, and this is falsé."
|
|
|
|
tokens = tokenizer.tokenize(sequence)
|
|
rust_tokens = rust_tokenizer.tokenize(sequence)
|
|
self.assertListEqual(tokens, rust_tokens)
|
|
|
|
ids = tokenizer.encode(sequence, add_special_tokens=False)
|
|
rust_ids = rust_tokenizer.encode(sequence, add_special_tokens=False)
|
|
self.assertListEqual(ids, rust_ids)
|
|
|
|
rust_tokenizer = self.get_rust_tokenizer()
|
|
ids = tokenizer.encode(sequence)
|
|
rust_ids = rust_tokenizer.encode(sequence)
|
|
self.assertListEqual(ids, rust_ids)
|
|
|
|
def test_full_tokenizer(self):
|
|
tokenizer = AlbertTokenizer(SAMPLE_VOCAB, keep_accents=True)
|
|
|
|
tokens = tokenizer.tokenize("This is a test")
|
|
self.assertListEqual(tokens, ["▁this", "▁is", "▁a", "▁test"])
|
|
|
|
self.assertListEqual(tokenizer.convert_tokens_to_ids(tokens), [48, 25, 21, 1289])
|
|
|
|
tokens = tokenizer.tokenize("I was born in 92000, and this is falsé.")
|
|
self.assertListEqual(
|
|
tokens, ["▁i", "▁was", "▁born", "▁in", "▁9", "2000", ",", "▁and", "▁this", "▁is", "▁fal", "s", "é", "."]
|
|
)
|
|
ids = tokenizer.convert_tokens_to_ids(tokens)
|
|
self.assertListEqual(ids, [31, 23, 386, 19, 561, 3050, 15, 17, 48, 25, 8256, 18, 1, 9])
|
|
|
|
back_tokens = tokenizer.convert_ids_to_tokens(ids)
|
|
self.assertListEqual(
|
|
back_tokens,
|
|
["▁i", "▁was", "▁born", "▁in", "▁9", "2000", ",", "▁and", "▁this", "▁is", "▁fal", "s", "<unk>", "."],
|
|
)
|
|
|
|
def test_sequence_builders(self):
|
|
tokenizer = AlbertTokenizer(SAMPLE_VOCAB)
|
|
|
|
text = tokenizer.encode("sequence builders")
|
|
text_2 = tokenizer.encode("multi-sequence build")
|
|
|
|
encoded_sentence = tokenizer.build_inputs_with_special_tokens(text)
|
|
encoded_pair = tokenizer.build_inputs_with_special_tokens(text, text_2)
|
|
|
|
assert encoded_sentence == [tokenizer.cls_token_id] + text + [tokenizer.sep_token_id]
|
|
assert encoded_pair == [tokenizer.cls_token_id] + text + [tokenizer.sep_token_id] + text_2 + [
|
|
tokenizer.sep_token_id
|
|
]
|
|
|
|
@slow
|
|
def test_tokenizer_integration(self):
|
|
tokenizer_classes = [self.tokenizer_class]
|
|
if self.test_rust_tokenizer:
|
|
tokenizer_classes.append(self.rust_tokenizer_class)
|
|
|
|
for tokenizer_class in tokenizer_classes:
|
|
tokenizer = tokenizer_class.from_pretrained("albert-base-v2")
|
|
|
|
sequences = [
|
|
"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations",
|
|
"ALBERT incorporates two parameter reduction techniques",
|
|
"The first one is a factorized embedding parameterization. By decomposing the large vocabulary embedding matrix into two small matrices, we separate the size of the hidden layers from the size of vocabulary embedding.", # noqa: E231
|
|
]
|
|
|
|
encoding = tokenizer(sequences, padding=True)
|
|
decoded_sequences = [tokenizer.decode(seq, skip_special_tokens=True) for seq in encoding["input_ids"]]
|
|
|
|
# fmt: off
|
|
expected_encoding = {
|
|
'input_ids': [
|
|
[2, 2953, 45, 21, 13, 10601, 11502, 26, 1119, 8, 8542, 3762, 69, 2477, 16, 816, 18667, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], # noqa: E231
|
|
[2, 2953, 13760, 81, 18906, 5895, 4212, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], # noqa: E231
|
|
[2, 14, 64, 53, 25, 21, 3932, 1333, 11911, 69, 3258, 18906, 1829, 9, 34, 121, 960, 14717, 14, 370, 18630, 11911, 69, 3258, 8187, 77, 81, 284, 24849, 15, 95, 1725, 14, 1072, 16, 14, 3689, 9124, 37, 14, 1072, 16, 18630, 11911, 69, 3258, 9, 3]], # noqa: E231
|
|
'token_type_ids': [
|
|
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], # noqa: E231
|
|
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], # noqa: E231
|
|
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], # noqa: E231
|
|
'attention_mask': [
|
|
[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], # noqa: E231
|
|
[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], # noqa: E231
|
|
[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: E231
|
|
]
|
|
}
|
|
|
|
expected_decoded_sequence = [
|
|
"albert: a lite bert for self-supervised learning of language representations",
|
|
'albert incorporates two parameter reduction techniques',
|
|
'the first one is a factorized embedding parameterization. by decomposing the large vocabulary embedding matrix into two small matrices, we separate the size of the hidden layers from the size of vocabulary embedding.' # noqa: E231
|
|
]
|
|
# fmt: on
|
|
|
|
self.assertDictEqual(encoding.data, expected_encoding)
|
|
|
|
for expected, decoded in zip(expected_decoded_sequence, decoded_sequences):
|
|
self.assertEqual(expected, decoded)
|