|
| 1 | +/* Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved. |
| 2 | +
|
| 3 | +Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 | +you may not use this file except in compliance with the License. |
| 5 | +You may obtain a copy of the License at |
| 6 | +
|
| 7 | + http://www.apache.org/licenses/LICENSE-2.0 |
| 8 | +
|
| 9 | +Unless required by applicable law or agreed to in writing, software |
| 10 | +distributed under the License is distributed on an "AS IS" BASIS, |
| 11 | +WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 12 | +See the License for the specific language governing permissions and |
| 13 | +limitations under the License. */ |
| 14 | +#pragma once |
| 15 | + |
| 16 | +#include <string> |
| 17 | +#include <unordered_map> |
| 18 | +#include "core/tokenizer.h" |
| 19 | + |
| 20 | +namespace tokenizers { |
| 21 | +namespace tokenizers_impl { |
| 22 | + |
| 23 | +struct ErnieFasterTokenizer : public core::Tokenizer { |
| 24 | + ErnieFasterTokenizer(const std::string& vocab_path, |
| 25 | + const std::string& unk_token = "[UNK]", |
| 26 | + const std::string& sep_token = "[SEP]", |
| 27 | + const std::string& cls_token = "[CLS]", |
| 28 | + const std::string& pad_token = "[PAD]", |
| 29 | + const std::string& mask_token = "[MASK]", |
| 30 | + bool clean_text = true, |
| 31 | + bool handle_chinese_chars = true, |
| 32 | + bool strip_accents = true, |
| 33 | + bool lowercase = true, |
| 34 | + const std::string& wordpieces_prefix = "##", |
| 35 | + uint max_sequence_len = 0); |
| 36 | + |
| 37 | + ErnieFasterTokenizer(const core::Vocab& vocab, |
| 38 | + const std::string& unk_token = "[UNK]", |
| 39 | + const std::string& sep_token = "[SEP]", |
| 40 | + const std::string& cls_token = "[CLS]", |
| 41 | + const std::string& pad_token = "[PAD]", |
| 42 | + const std::string& mask_token = "[MASK]", |
| 43 | + bool clean_text = true, |
| 44 | + bool handle_chinese_chars = true, |
| 45 | + bool strip_accents = true, |
| 46 | + bool lowercase = true, |
| 47 | + const std::string& wordpieces_prefix = "##", |
| 48 | + uint max_sequence_len = 0); |
| 49 | + |
| 50 | +private: |
| 51 | + void Init(const core::Vocab& vocab, |
| 52 | + const std::string& unk_token = "[UNK]", |
| 53 | + const std::string& sep_token = "[SEP]", |
| 54 | + const std::string& cls_token = "[CLS]", |
| 55 | + const std::string& pad_token = "[PAD]", |
| 56 | + const std::string& mask_token = "[MASK]", |
| 57 | + bool clean_text = true, |
| 58 | + bool handle_chinese_chars = true, |
| 59 | + bool strip_accents = true, |
| 60 | + bool lowercase = true, |
| 61 | + const std::string& wordpieces_prefix = "##", |
| 62 | + uint max_sequence_len = 0); |
| 63 | +}; |
| 64 | + |
| 65 | +} // tokenizers_impl |
| 66 | +} // tokenizers |
0 commit comments