File size: 9,795 Bytes
7934b29 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
# Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.
#
# 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 pytest
from nemo.collections.common.tokenizers.sentencepiece_tokenizer import SentencePieceTokenizer
from nemo.collections.common.tokenizers.youtokentome_tokenizer import YouTokenToMeTokenizer
MODEL_SPECIAL_TOKENS = {
'unk_token': '[UNK]',
'sep_token': '[SEP]',
'pad_token': '[PAD]',
'bos_token': '[CLS]',
'mask_token': '[MASK]',
'eos_token': '[SEP]',
'cls_token': '[CLS]',
}
class TestSentencePieceTokenizerLegacy:
model_name = "/m_common.model"
@pytest.mark.unit
def test_add_special_tokens(self, test_data_dir):
tokenizer = SentencePieceTokenizer(test_data_dir + self.model_name, legacy=True)
special_tokens = MODEL_SPECIAL_TOKENS
tokenizer.add_special_tokens(special_tokens)
assert tokenizer.vocab_size == tokenizer.original_vocab_size + len(set(special_tokens.values()))
@pytest.mark.unit
def test_text_to_tokens(self, test_data_dir):
tokenizer = SentencePieceTokenizer(test_data_dir + self.model_name, legacy=True)
special_tokens = MODEL_SPECIAL_TOKENS
tokenizer.add_special_tokens(special_tokens)
text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]"
tokens = tokenizer.text_to_tokens(text)
assert len(tokens) == len(text.split())
assert tokens.count("[CLS]") == 1
assert tokens.count("[MASK]") == 1
assert tokens.count("[SEP]") == 2
@pytest.mark.unit
def test_tokens_to_text(self, test_data_dir):
tokenizer = SentencePieceTokenizer(test_data_dir + self.model_name, legacy=True)
text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]"
tokens = tokenizer.text_to_tokens(text)
result = tokenizer.tokens_to_text(tokens)
assert text == result
@pytest.mark.unit
def test_text_to_ids(self, test_data_dir):
tokenizer = SentencePieceTokenizer(test_data_dir + self.model_name, legacy=True)
special_tokens = MODEL_SPECIAL_TOKENS
tokenizer.add_special_tokens(special_tokens)
text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]"
ids = tokenizer.text_to_ids(text)
assert len(ids) == len(text.split())
assert ids.count(tokenizer.token_to_id("[CLS]")) == 1
assert ids.count(tokenizer.token_to_id("[MASK]")) == 1
assert ids.count(tokenizer.token_to_id("[SEP]")) == 2
@pytest.mark.unit
def test_ids_to_text(self, test_data_dir):
tokenizer = SentencePieceTokenizer(test_data_dir + self.model_name, legacy=True)
special_tokens = MODEL_SPECIAL_TOKENS
tokenizer.add_special_tokens(special_tokens)
text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]"
ids = tokenizer.text_to_ids(text)
result = tokenizer.ids_to_text(ids)
assert text == result
@pytest.mark.unit
def test_tokens_to_ids(self, test_data_dir):
tokenizer = SentencePieceTokenizer(test_data_dir + self.model_name, legacy=True)
special_tokens = MODEL_SPECIAL_TOKENS
tokenizer.add_special_tokens(special_tokens)
text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]"
tokens = tokenizer.text_to_tokens(text)
ids = tokenizer.tokens_to_ids(tokens)
assert len(ids) == len(tokens)
assert ids.count(tokenizer.token_to_id("[CLS]")) == 1
assert ids.count(tokenizer.token_to_id("[MASK]")) == 1
assert ids.count(tokenizer.token_to_id("[SEP]")) == 2
@pytest.mark.unit
def test_ids_to_tokens(self, test_data_dir):
tokenizer = SentencePieceTokenizer(test_data_dir + self.model_name, legacy=True)
special_tokens = MODEL_SPECIAL_TOKENS
tokenizer.add_special_tokens(special_tokens)
text = "[CLS] a b c [MASK] e f [SEP] g h i [SEP]"
tokens = tokenizer.text_to_tokens(text)
ids = tokenizer.tokens_to_ids(tokens)
result = tokenizer.ids_to_tokens(ids)
assert len(result) == len(tokens)
for i in range(len(result)):
assert result[i] == tokens[i]
class TestSentencePieceTokenizer:
model_name = "/m_new.model"
@pytest.mark.unit
def test_text_to_tokens(self, test_data_dir):
tokenizer = SentencePieceTokenizer(test_data_dir + self.model_name)
# <cls> is user_defined_symbol in the test tokenizer model
# <unk>, <sep>, <s>, and </s> are control symbols
text = "<cls> a b c <sep> e f g h i </s>"
tokens = tokenizer.text_to_tokens(text)
assert tokens.count("<cls>") == 1
assert tokens.count("<sep>") == 0
assert tokens.count("</s>") == 0
@pytest.mark.unit
def test_tokens_to_text(self, test_data_dir):
tokenizer = SentencePieceTokenizer(test_data_dir + self.model_name)
# <cls> is user_defined_symbol in the test tokenizer model
text = "<cls> a b c e f g h i"
tokens = tokenizer.text_to_tokens(text)
result = tokenizer.tokens_to_text(tokens)
assert text == result
@pytest.mark.unit
def test_text_to_ids(self, test_data_dir):
tokenizer = SentencePieceTokenizer(test_data_dir + self.model_name)
# <cls> is user_defined_symbol in the test tokenizer model
# <unk>, <sep>, <s>, and </s> are control symbols
text = "<cls> a b c <sep> e f g h i </s>"
tokens = tokenizer.text_to_ids(text)
assert tokens.count(tokenizer.token_to_id("<cls>")) == 1
assert tokens.count(tokenizer.token_to_id("<sep>")) == 0
assert tokens.count(tokenizer.token_to_id("</s>")) == 0
@pytest.mark.unit
def test_ids_to_text(self, test_data_dir):
tokenizer = SentencePieceTokenizer(test_data_dir + self.model_name)
text = "<cls> a b c <sep> e f g h i </s>"
ids = tokenizer.text_to_ids(text)
result = tokenizer.ids_to_text(ids)
assert text == result
@pytest.mark.unit
def test_tokens_to_ids(self, test_data_dir):
tokenizer = SentencePieceTokenizer(test_data_dir + self.model_name)
tokens = ["<cls>", "a", "b", "c", "<sep>", "e", "f", "<sep>", "g", "h", "i", "</s>"]
ids = tokenizer.tokens_to_ids(tokens)
assert len(ids) == len(tokens)
assert ids.count(tokenizer.token_to_id("<cls>")) == 1
assert ids.count(tokenizer.token_to_id("</s>")) == 1
assert ids.count(tokenizer.token_to_id("<sep>")) == 2
@pytest.mark.unit
def test_ids_to_tokens(self, test_data_dir):
tokenizer = SentencePieceTokenizer(test_data_dir + self.model_name)
tokens = ["<cls>", "a", "b", "c", "<sep>", "e", "f", "<sep>", "g", "h", "i", "</s>"]
ids = tokenizer.tokens_to_ids(tokens)
result = tokenizer.ids_to_tokens(ids)
assert len(result) == len(tokens)
for i in range(len(result)):
assert result[i] == tokens[i]
class TestYouTokenToMeTokenizer:
model_name = "/yttm.4096.en-de.model"
@pytest.mark.unit
def test_text_to_tokens(self, test_data_dir):
tokenizer = YouTokenToMeTokenizer(test_data_dir + self.model_name)
text = "<BOS> a b c e <UNK> f g h i <EOS>"
tokens = tokenizer.text_to_tokens(text)
assert tokens.count("<BOS>") == 0
assert tokens.count("<UNK>") == 0
assert tokens.count("<EOS>") == 0
@pytest.mark.unit
def test_tokens_to_text(self, test_data_dir):
tokenizer = YouTokenToMeTokenizer(test_data_dir + self.model_name)
text = "a b c e f g h i"
tokens = tokenizer.text_to_tokens(text)
result = tokenizer.tokens_to_text(tokens)
assert text == result
@pytest.mark.unit
def test_text_to_ids(self, test_data_dir):
tokenizer = YouTokenToMeTokenizer(test_data_dir + self.model_name)
text = "<BOS> a b c <UNK> e f g h i <EOS>"
tokens = tokenizer.text_to_ids(text)
assert tokens.count(tokenizer.bos_id) == 0
assert tokens.count(tokenizer.unk_id) == 0
assert tokens.count(tokenizer.eos_id) == 0
@pytest.mark.unit
def test_ids_to_text(self, test_data_dir):
tokenizer = YouTokenToMeTokenizer(test_data_dir + self.model_name)
text = "a b c e f g h i"
ids = tokenizer.text_to_ids(text)
result = tokenizer.ids_to_text(ids)
assert text == result
@pytest.mark.unit
def test_tokens_to_ids(self, test_data_dir):
tokenizer = YouTokenToMeTokenizer(test_data_dir + self.model_name)
tokens = ["<BOS>", "a", "b", "c", "<UNK>", "e", "f", "<UNK>", "g", "h", "i", "<EOS>"]
ids = tokenizer.tokens_to_ids(tokens)
assert len(ids) == len(tokens)
assert ids.count(tokenizer.bos_id) == 1
assert ids.count(tokenizer.eos_id) == 1
assert ids.count(tokenizer.unk_id) == 2
@pytest.mark.unit
def test_ids_to_tokens(self, test_data_dir):
tokenizer = YouTokenToMeTokenizer(test_data_dir + self.model_name)
tokens = ["<BOS>", "a", "b", "c", "<UNK>", "e", "f", "<UNK>", "g", "h", "i", "<EOS>"]
ids = tokenizer.tokens_to_ids(tokens)
result = tokenizer.ids_to_tokens(ids)
assert len(result) == len(tokens)
for i in range(len(result)):
assert result[i] == tokens[i]
|