Spaces:
Runtime error
Runtime error
File size: 6,385 Bytes
455a40f |
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 |
# Copyright 2022 The HuggingFace Team. 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 json
import os
import shutil
import tempfile
import unittest
from transformers import MCTCTProcessor, is_speech_available, is_torch_available
from transformers.file_utils import FEATURE_EXTRACTOR_NAME
from transformers.models.wav2vec2.tokenization_wav2vec2 import VOCAB_FILES_NAMES, Wav2Vec2CTCTokenizer
from transformers.testing_utils import require_torch, require_torchaudio
if is_speech_available() and is_torch_available():
from transformers import MCTCTFeatureExtractor
from .test_feature_extraction_mctct import floats_list
@require_torch
@require_torchaudio
class MCTCTProcessorTest(unittest.TestCase):
def setUp(self):
vocab = "<pad> <s> </s> <unk> | E T A O N I H S R D L U M W C F G Y P B V K ' X J Q Z".split(" ")
vocab_tokens = dict(zip(vocab, range(len(vocab))))
self.add_kwargs_tokens_map = {
"pad_token": "<pad>",
"unk_token": "<unk>",
"bos_token": "<s>",
"eos_token": "</s>",
}
feature_extractor_map = {
"feature_size": 1,
"padding_value": 0.0,
"sampling_rate": 16000,
"return_attention_mask": False,
"do_normalize": True,
}
self.tmpdirname = tempfile.mkdtemp()
self.vocab_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["vocab_file"])
self.feature_extraction_file = os.path.join(self.tmpdirname, FEATURE_EXTRACTOR_NAME)
with open(self.vocab_file, "w", encoding="utf-8") as fp:
fp.write(json.dumps(vocab_tokens) + "\n")
with open(self.feature_extraction_file, "w", encoding="utf-8") as fp:
fp.write(json.dumps(feature_extractor_map) + "\n")
def get_tokenizer(self, **kwargs_init):
kwargs = self.add_kwargs_tokens_map.copy()
kwargs.update(kwargs_init)
return Wav2Vec2CTCTokenizer.from_pretrained(self.tmpdirname, **kwargs)
def get_feature_extractor(self, **kwargs):
return MCTCTFeatureExtractor.from_pretrained(self.tmpdirname, **kwargs)
def tearDown(self):
shutil.rmtree(self.tmpdirname)
def test_save_load_pretrained_default(self):
tokenizer = self.get_tokenizer()
feature_extractor = self.get_feature_extractor()
processor = MCTCTProcessor(tokenizer=tokenizer, feature_extractor=feature_extractor)
processor.save_pretrained(self.tmpdirname)
processor = MCTCTProcessor.from_pretrained(self.tmpdirname)
self.assertEqual(processor.tokenizer.get_vocab(), tokenizer.get_vocab())
self.assertIsInstance(processor.tokenizer, Wav2Vec2CTCTokenizer)
self.assertEqual(processor.feature_extractor.to_json_string(), feature_extractor.to_json_string())
self.assertIsInstance(processor.feature_extractor, MCTCTFeatureExtractor)
def test_save_load_pretrained_additional_features(self):
processor = MCTCTProcessor(tokenizer=self.get_tokenizer(), feature_extractor=self.get_feature_extractor())
processor.save_pretrained(self.tmpdirname)
tokenizer_add_kwargs = self.get_tokenizer(bos_token="(BOS)", eos_token="(EOS)")
feature_extractor_add_kwargs = self.get_feature_extractor(do_normalize=False, padding_value=1.0)
processor = MCTCTProcessor.from_pretrained(
self.tmpdirname, bos_token="(BOS)", eos_token="(EOS)", do_normalize=False, padding_value=1.0
)
self.assertEqual(processor.tokenizer.get_vocab(), tokenizer_add_kwargs.get_vocab())
self.assertIsInstance(processor.tokenizer, Wav2Vec2CTCTokenizer)
self.assertEqual(processor.feature_extractor.to_json_string(), feature_extractor_add_kwargs.to_json_string())
self.assertIsInstance(processor.feature_extractor, MCTCTFeatureExtractor)
def test_feature_extractor(self):
feature_extractor = self.get_feature_extractor()
tokenizer = self.get_tokenizer()
processor = MCTCTProcessor(tokenizer=tokenizer, feature_extractor=feature_extractor)
raw_speech = floats_list((3, 1000))
input_feat_extract = feature_extractor(raw_speech, return_tensors="np")
input_processor = processor(raw_speech, return_tensors="np")
for key in input_feat_extract.keys():
self.assertAlmostEqual(input_feat_extract[key].sum(), input_processor[key].sum(), delta=1e-2)
def test_tokenizer(self):
feature_extractor = self.get_feature_extractor()
tokenizer = self.get_tokenizer()
processor = MCTCTProcessor(tokenizer=tokenizer, feature_extractor=feature_extractor)
input_str = "This is a test string"
encoded_processor = processor(text=input_str)
encoded_tok = tokenizer(input_str)
for key in encoded_tok.keys():
self.assertListEqual(encoded_tok[key], encoded_processor[key])
def test_tokenizer_decode(self):
feature_extractor = self.get_feature_extractor()
tokenizer = self.get_tokenizer()
processor = MCTCTProcessor(tokenizer=tokenizer, feature_extractor=feature_extractor)
predicted_ids = [[1, 4, 5, 8, 1, 0, 8], [3, 4, 3, 1, 1, 8, 9]]
decoded_processor = processor.batch_decode(predicted_ids)
decoded_tok = tokenizer.batch_decode(predicted_ids)
self.assertListEqual(decoded_tok, decoded_processor)
def test_model_input_names(self):
feature_extractor = self.get_feature_extractor()
tokenizer = self.get_tokenizer()
processor = MCTCTProcessor(tokenizer=tokenizer, feature_extractor=feature_extractor)
self.assertListEqual(
processor.model_input_names,
feature_extractor.model_input_names,
msg="`processor` and `feature_extractor` model input names do not match",
)
|