Fine-tuned bulu translation model
Browse files- README.md +61 -0
- config.json +60 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- runs/Apr26_14-33-38_9c13ea6c2dcd/events.out.tfevents.1745678019.9c13ea6c2dcd.1131.0 +3 -0
- runs/Apr26_14-33-38_9c13ea6c2dcd/events.out.tfevents.1745678627.9c13ea6c2dcd.1131.1 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +1650 -0
- tokenizer_config.json +1240 -0
- training_args.bin +3 -0
- vocab.txt +153 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: t5-small
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: bulu_translation
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# bulu_translation
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.1097
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0003
|
| 39 |
+
- train_batch_size: 16
|
| 40 |
+
- eval_batch_size: 16
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 3
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 0.1238 | 1.0 | 1565 | 0.1131 |
|
| 52 |
+
| 0.114 | 2.0 | 3130 | 0.1125 |
|
| 53 |
+
| 0.1123 | 3.0 | 4695 | 0.1106 |
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- Transformers 4.51.3
|
| 59 |
+
- Pytorch 2.6.0+cu124
|
| 60 |
+
- Datasets 3.5.0
|
| 61 |
+
- Tokenizers 0.21.1
|
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"T5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"classifier_dropout": 0.0,
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 512,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "relu",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "relu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": false,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "t5",
|
| 19 |
+
"n_positions": 512,
|
| 20 |
+
"num_decoder_layers": 6,
|
| 21 |
+
"num_heads": 8,
|
| 22 |
+
"num_layers": 6,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"task_specific_params": {
|
| 28 |
+
"summarization": {
|
| 29 |
+
"early_stopping": true,
|
| 30 |
+
"length_penalty": 2.0,
|
| 31 |
+
"max_length": 200,
|
| 32 |
+
"min_length": 30,
|
| 33 |
+
"no_repeat_ngram_size": 3,
|
| 34 |
+
"num_beams": 4,
|
| 35 |
+
"prefix": "summarize: "
|
| 36 |
+
},
|
| 37 |
+
"translation_en_to_de": {
|
| 38 |
+
"early_stopping": true,
|
| 39 |
+
"max_length": 300,
|
| 40 |
+
"num_beams": 4,
|
| 41 |
+
"prefix": "translate English to German: "
|
| 42 |
+
},
|
| 43 |
+
"translation_en_to_fr": {
|
| 44 |
+
"early_stopping": true,
|
| 45 |
+
"max_length": 300,
|
| 46 |
+
"num_beams": 4,
|
| 47 |
+
"prefix": "translate English to French: "
|
| 48 |
+
},
|
| 49 |
+
"translation_en_to_ro": {
|
| 50 |
+
"early_stopping": true,
|
| 51 |
+
"max_length": 300,
|
| 52 |
+
"num_beams": 4,
|
| 53 |
+
"prefix": "translate English to Romanian: "
|
| 54 |
+
}
|
| 55 |
+
},
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.51.3",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 153
|
| 60 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.51.3"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f7d171cc6eb09e0ddfda28a30fb0a1fab903300582aca05c09dc8f87b8623da
|
| 3 |
+
size 176557096
|
runs/Apr26_14-33-38_9c13ea6c2dcd/events.out.tfevents.1745678019.9c13ea6c2dcd.1131.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13255d59e47654adf22d0765e65c6f25c6797b4f7fb7960011242dc912c65d96
|
| 3 |
+
size 9047
|
runs/Apr26_14-33-38_9c13ea6c2dcd/events.out.tfevents.1745678627.9c13ea6c2dcd.1131.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7079782aecba6771cedd120e2f899fb3478939126386470b1b72cd987600117
|
| 3 |
+
size 359
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,1650 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 128,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 128
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 1,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "[PAD]"
|
| 18 |
+
},
|
| 19 |
+
"added_tokens": [
|
| 20 |
+
{
|
| 21 |
+
"id": 0,
|
| 22 |
+
"content": "[UNK]",
|
| 23 |
+
"single_word": false,
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"id": 1,
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"id": 2,
|
| 40 |
+
"content": "[CLS]",
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"lstrip": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"normalized": false,
|
| 45 |
+
"special": true
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"id": 3,
|
| 49 |
+
"content": "[SEP]",
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"lstrip": false,
|
| 52 |
+
"rstrip": false,
|
| 53 |
+
"normalized": false,
|
| 54 |
+
"special": true
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"id": 4,
|
| 58 |
+
"content": "[MASK]",
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"lstrip": false,
|
| 61 |
+
"rstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"special": true
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"id": 5,
|
| 67 |
+
"content": "[p]",
|
| 68 |
+
"single_word": false,
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"special": true
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"id": 6,
|
| 76 |
+
"content": "[b]",
|
| 77 |
+
"single_word": false,
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"id": 7,
|
| 85 |
+
"content": "[t]",
|
| 86 |
+
"single_word": false,
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"id": 8,
|
| 94 |
+
"content": "[d]",
|
| 95 |
+
"single_word": false,
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"normalized": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"id": 9,
|
| 103 |
+
"content": "[ʈ]",
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"lstrip": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"id": 10,
|
| 112 |
+
"content": "[ɖ]",
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"lstrip": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"normalized": false,
|
| 117 |
+
"special": true
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"id": 11,
|
| 121 |
+
"content": "[c]",
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"lstrip": false,
|
| 124 |
+
"rstrip": false,
|
| 125 |
+
"normalized": false,
|
| 126 |
+
"special": true
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"id": 12,
|
| 130 |
+
"content": "[ɟ]",
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"lstrip": false,
|
| 133 |
+
"rstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"special": true
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"id": 13,
|
| 139 |
+
"content": "[k]",
|
| 140 |
+
"single_word": false,
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"rstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"special": true
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"id": 14,
|
| 148 |
+
"content": "[g]",
|
| 149 |
+
"single_word": false,
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"id": 15,
|
| 157 |
+
"content": "[q]",
|
| 158 |
+
"single_word": false,
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"id": 16,
|
| 166 |
+
"content": "[ɢ]",
|
| 167 |
+
"single_word": false,
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"normalized": false,
|
| 171 |
+
"special": true
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"id": 17,
|
| 175 |
+
"content": "[ʔ]",
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"lstrip": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"normalized": false,
|
| 180 |
+
"special": true
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"id": 18,
|
| 184 |
+
"content": "[m]",
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"lstrip": false,
|
| 187 |
+
"rstrip": false,
|
| 188 |
+
"normalized": false,
|
| 189 |
+
"special": true
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"id": 19,
|
| 193 |
+
"content": "[ɱ]",
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"lstrip": false,
|
| 196 |
+
"rstrip": false,
|
| 197 |
+
"normalized": false,
|
| 198 |
+
"special": true
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"id": 20,
|
| 202 |
+
"content": "[n]",
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"lstrip": false,
|
| 205 |
+
"rstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"special": true
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"id": 21,
|
| 211 |
+
"content": "[ɳ]",
|
| 212 |
+
"single_word": false,
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"rstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"special": true
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"id": 22,
|
| 220 |
+
"content": "[ɲ]",
|
| 221 |
+
"single_word": false,
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"id": 23,
|
| 229 |
+
"content": "[ŋ]",
|
| 230 |
+
"single_word": false,
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"id": 24,
|
| 238 |
+
"content": "[ɴ]",
|
| 239 |
+
"single_word": false,
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"normalized": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"id": 25,
|
| 247 |
+
"content": "[ʙ]",
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"lstrip": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"normalized": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"id": 26,
|
| 256 |
+
"content": "[r]",
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"lstrip": false,
|
| 259 |
+
"rstrip": false,
|
| 260 |
+
"normalized": false,
|
| 261 |
+
"special": true
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"id": 27,
|
| 265 |
+
"content": "[ʀ]",
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"lstrip": false,
|
| 268 |
+
"rstrip": false,
|
| 269 |
+
"normalized": false,
|
| 270 |
+
"special": true
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"id": 28,
|
| 274 |
+
"content": "[ɾ]",
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"lstrip": false,
|
| 277 |
+
"rstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"special": true
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"id": 29,
|
| 283 |
+
"content": "[ɽ]",
|
| 284 |
+
"single_word": false,
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"rstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"special": true
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"id": 30,
|
| 292 |
+
"content": "[ɸ]",
|
| 293 |
+
"single_word": false,
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"id": 31,
|
| 301 |
+
"content": "[β]",
|
| 302 |
+
"single_word": false,
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"normalized": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"id": 32,
|
| 310 |
+
"content": "[f]",
|
| 311 |
+
"single_word": false,
|
| 312 |
+
"lstrip": false,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"normalized": false,
|
| 315 |
+
"special": true
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"id": 33,
|
| 319 |
+
"content": "[v]",
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"lstrip": false,
|
| 322 |
+
"rstrip": false,
|
| 323 |
+
"normalized": false,
|
| 324 |
+
"special": true
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"id": 34,
|
| 328 |
+
"content": "[θ]",
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"lstrip": false,
|
| 331 |
+
"rstrip": false,
|
| 332 |
+
"normalized": false,
|
| 333 |
+
"special": true
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"id": 35,
|
| 337 |
+
"content": "[ð]",
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"lstrip": false,
|
| 340 |
+
"rstrip": false,
|
| 341 |
+
"normalized": false,
|
| 342 |
+
"special": true
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"id": 36,
|
| 346 |
+
"content": "[s]",
|
| 347 |
+
"single_word": false,
|
| 348 |
+
"lstrip": false,
|
| 349 |
+
"rstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"special": true
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"id": 37,
|
| 355 |
+
"content": "[z]",
|
| 356 |
+
"single_word": false,
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"rstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"special": true
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"id": 38,
|
| 364 |
+
"content": "[ʃ]",
|
| 365 |
+
"single_word": false,
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"id": 39,
|
| 373 |
+
"content": "[ʒ]",
|
| 374 |
+
"single_word": false,
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"normalized": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"id": 40,
|
| 382 |
+
"content": "[ʂ]",
|
| 383 |
+
"single_word": false,
|
| 384 |
+
"lstrip": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"normalized": false,
|
| 387 |
+
"special": true
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"id": 41,
|
| 391 |
+
"content": "[ʐ]",
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"lstrip": false,
|
| 394 |
+
"rstrip": false,
|
| 395 |
+
"normalized": false,
|
| 396 |
+
"special": true
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"id": 42,
|
| 400 |
+
"content": "[ç]",
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"lstrip": false,
|
| 403 |
+
"rstrip": false,
|
| 404 |
+
"normalized": false,
|
| 405 |
+
"special": true
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"id": 43,
|
| 409 |
+
"content": "[ʝ]",
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"lstrip": false,
|
| 412 |
+
"rstrip": false,
|
| 413 |
+
"normalized": false,
|
| 414 |
+
"special": true
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"id": 44,
|
| 418 |
+
"content": "[x]",
|
| 419 |
+
"single_word": false,
|
| 420 |
+
"lstrip": false,
|
| 421 |
+
"rstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"special": true
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"id": 45,
|
| 427 |
+
"content": "[ɣ]",
|
| 428 |
+
"single_word": false,
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"rstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"special": true
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"id": 46,
|
| 436 |
+
"content": "[χ]",
|
| 437 |
+
"single_word": false,
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"id": 47,
|
| 445 |
+
"content": "[ʁ]",
|
| 446 |
+
"single_word": false,
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"normalized": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"id": 48,
|
| 454 |
+
"content": "[ħ]",
|
| 455 |
+
"single_word": false,
|
| 456 |
+
"lstrip": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"normalized": false,
|
| 459 |
+
"special": true
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"id": 49,
|
| 463 |
+
"content": "[ʕ]",
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"lstrip": false,
|
| 466 |
+
"rstrip": false,
|
| 467 |
+
"normalized": false,
|
| 468 |
+
"special": true
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"id": 50,
|
| 472 |
+
"content": "[h]",
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"lstrip": false,
|
| 475 |
+
"rstrip": false,
|
| 476 |
+
"normalized": false,
|
| 477 |
+
"special": true
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"id": 51,
|
| 481 |
+
"content": "[ɦ]",
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"lstrip": false,
|
| 484 |
+
"rstrip": false,
|
| 485 |
+
"normalized": false,
|
| 486 |
+
"special": true
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"id": 52,
|
| 490 |
+
"content": "[ɬ]",
|
| 491 |
+
"single_word": false,
|
| 492 |
+
"lstrip": false,
|
| 493 |
+
"rstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"special": true
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"id": 53,
|
| 499 |
+
"content": "[ɮ]",
|
| 500 |
+
"single_word": false,
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"rstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"special": true
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"id": 54,
|
| 508 |
+
"content": "[ʋ]",
|
| 509 |
+
"single_word": false,
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"normalized": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"id": 55,
|
| 517 |
+
"content": "[ɹ]",
|
| 518 |
+
"single_word": false,
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"normalized": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"id": 56,
|
| 526 |
+
"content": "[ɻ]",
|
| 527 |
+
"single_word": false,
|
| 528 |
+
"lstrip": false,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"normalized": false,
|
| 531 |
+
"special": true
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"id": 57,
|
| 535 |
+
"content": "[j]",
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"lstrip": false,
|
| 538 |
+
"rstrip": false,
|
| 539 |
+
"normalized": false,
|
| 540 |
+
"special": true
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"id": 58,
|
| 544 |
+
"content": "[ɰ]",
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"lstrip": false,
|
| 547 |
+
"rstrip": false,
|
| 548 |
+
"normalized": false,
|
| 549 |
+
"special": true
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"id": 59,
|
| 553 |
+
"content": "[l]",
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"lstrip": false,
|
| 556 |
+
"rstrip": false,
|
| 557 |
+
"normalized": false,
|
| 558 |
+
"special": true
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"id": 60,
|
| 562 |
+
"content": "[ɭ]",
|
| 563 |
+
"single_word": false,
|
| 564 |
+
"lstrip": false,
|
| 565 |
+
"rstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"special": true
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"id": 61,
|
| 571 |
+
"content": "[ʎ]",
|
| 572 |
+
"single_word": false,
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"rstrip": false,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"special": true
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"id": 62,
|
| 580 |
+
"content": "[ʟ]",
|
| 581 |
+
"single_word": false,
|
| 582 |
+
"lstrip": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"normalized": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"id": 63,
|
| 589 |
+
"content": "[ƥ]",
|
| 590 |
+
"single_word": false,
|
| 591 |
+
"lstrip": false,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"normalized": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"id": 64,
|
| 598 |
+
"content": "[ɓ]",
|
| 599 |
+
"single_word": false,
|
| 600 |
+
"lstrip": false,
|
| 601 |
+
"rstrip": false,
|
| 602 |
+
"normalized": false,
|
| 603 |
+
"special": true
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"id": 65,
|
| 607 |
+
"content": "[ƭ]",
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"lstrip": false,
|
| 610 |
+
"rstrip": false,
|
| 611 |
+
"normalized": false,
|
| 612 |
+
"special": true
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"id": 66,
|
| 616 |
+
"content": "[ɗ]",
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"lstrip": false,
|
| 619 |
+
"rstrip": false,
|
| 620 |
+
"normalized": false,
|
| 621 |
+
"special": true
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"id": 67,
|
| 625 |
+
"content": "[ƈ]",
|
| 626 |
+
"single_word": false,
|
| 627 |
+
"lstrip": false,
|
| 628 |
+
"rstrip": false,
|
| 629 |
+
"normalized": false,
|
| 630 |
+
"special": true
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"id": 68,
|
| 634 |
+
"content": "[ʄ]",
|
| 635 |
+
"single_word": false,
|
| 636 |
+
"lstrip": false,
|
| 637 |
+
"rstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"special": true
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"id": 69,
|
| 643 |
+
"content": "[ƙ]",
|
| 644 |
+
"single_word": false,
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"rstrip": false,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"special": true
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"id": 70,
|
| 652 |
+
"content": "[ɠ]",
|
| 653 |
+
"single_word": false,
|
| 654 |
+
"lstrip": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"normalized": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"id": 71,
|
| 661 |
+
"content": "[ʠ]",
|
| 662 |
+
"single_word": false,
|
| 663 |
+
"lstrip": false,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"normalized": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"id": 72,
|
| 670 |
+
"content": "[ʛ]",
|
| 671 |
+
"single_word": false,
|
| 672 |
+
"lstrip": false,
|
| 673 |
+
"rstrip": false,
|
| 674 |
+
"normalized": false,
|
| 675 |
+
"special": true
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"id": 73,
|
| 679 |
+
"content": "[i]",
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"lstrip": false,
|
| 682 |
+
"rstrip": false,
|
| 683 |
+
"normalized": false,
|
| 684 |
+
"special": true
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"id": 74,
|
| 688 |
+
"content": "[y]",
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"lstrip": false,
|
| 691 |
+
"rstrip": false,
|
| 692 |
+
"normalized": false,
|
| 693 |
+
"special": true
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"id": 75,
|
| 697 |
+
"content": "[ɨ]",
|
| 698 |
+
"single_word": false,
|
| 699 |
+
"lstrip": false,
|
| 700 |
+
"rstrip": false,
|
| 701 |
+
"normalized": false,
|
| 702 |
+
"special": true
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"id": 76,
|
| 706 |
+
"content": "[ʉ]",
|
| 707 |
+
"single_word": false,
|
| 708 |
+
"lstrip": false,
|
| 709 |
+
"rstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"special": true
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"id": 77,
|
| 715 |
+
"content": "[ɯ]",
|
| 716 |
+
"single_word": false,
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"rstrip": false,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"special": true
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"id": 78,
|
| 724 |
+
"content": "[u]",
|
| 725 |
+
"single_word": false,
|
| 726 |
+
"lstrip": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"normalized": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"id": 79,
|
| 733 |
+
"content": "[ɪ]",
|
| 734 |
+
"single_word": false,
|
| 735 |
+
"lstrip": false,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"normalized": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"id": 80,
|
| 742 |
+
"content": "[ʏ]",
|
| 743 |
+
"single_word": false,
|
| 744 |
+
"lstrip": false,
|
| 745 |
+
"rstrip": false,
|
| 746 |
+
"normalized": false,
|
| 747 |
+
"special": true
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"id": 81,
|
| 751 |
+
"content": "[ʊ]",
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"lstrip": false,
|
| 754 |
+
"rstrip": false,
|
| 755 |
+
"normalized": false,
|
| 756 |
+
"special": true
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"id": 82,
|
| 760 |
+
"content": "[e]",
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"lstrip": false,
|
| 763 |
+
"rstrip": false,
|
| 764 |
+
"normalized": false,
|
| 765 |
+
"special": true
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"id": 83,
|
| 769 |
+
"content": "[ø]",
|
| 770 |
+
"single_word": false,
|
| 771 |
+
"lstrip": false,
|
| 772 |
+
"rstrip": false,
|
| 773 |
+
"normalized": false,
|
| 774 |
+
"special": true
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"id": 84,
|
| 778 |
+
"content": "[ɘ]",
|
| 779 |
+
"single_word": false,
|
| 780 |
+
"lstrip": false,
|
| 781 |
+
"rstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"special": true
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"id": 85,
|
| 787 |
+
"content": "[ɵ]",
|
| 788 |
+
"single_word": false,
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"rstrip": false,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"special": true
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"id": 86,
|
| 796 |
+
"content": "[ɤ]",
|
| 797 |
+
"single_word": false,
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"normalized": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"id": 87,
|
| 805 |
+
"content": "[ə]",
|
| 806 |
+
"single_word": false,
|
| 807 |
+
"lstrip": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"normalized": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"id": 88,
|
| 814 |
+
"content": "[ɛ]",
|
| 815 |
+
"single_word": false,
|
| 816 |
+
"lstrip": false,
|
| 817 |
+
"rstrip": false,
|
| 818 |
+
"normalized": false,
|
| 819 |
+
"special": true
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"id": 89,
|
| 823 |
+
"content": "[œ]",
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"lstrip": false,
|
| 826 |
+
"rstrip": false,
|
| 827 |
+
"normalized": false,
|
| 828 |
+
"special": true
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"id": 90,
|
| 832 |
+
"content": "[ɜ]",
|
| 833 |
+
"single_word": false,
|
| 834 |
+
"lstrip": false,
|
| 835 |
+
"rstrip": false,
|
| 836 |
+
"normalized": false,
|
| 837 |
+
"special": true
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"id": 91,
|
| 841 |
+
"content": "[ɞ]",
|
| 842 |
+
"single_word": false,
|
| 843 |
+
"lstrip": false,
|
| 844 |
+
"rstrip": false,
|
| 845 |
+
"normalized": false,
|
| 846 |
+
"special": true
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"id": 92,
|
| 850 |
+
"content": "[ʌ]",
|
| 851 |
+
"single_word": false,
|
| 852 |
+
"lstrip": false,
|
| 853 |
+
"rstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"special": true
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"id": 93,
|
| 859 |
+
"content": "[ɔ]",
|
| 860 |
+
"single_word": false,
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"rstrip": false,
|
| 863 |
+
"normalized": false,
|
| 864 |
+
"special": true
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"id": 94,
|
| 868 |
+
"content": "[æ]",
|
| 869 |
+
"single_word": false,
|
| 870 |
+
"lstrip": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"normalized": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"id": 95,
|
| 877 |
+
"content": "[ɐ]",
|
| 878 |
+
"single_word": false,
|
| 879 |
+
"lstrip": false,
|
| 880 |
+
"rstrip": false,
|
| 881 |
+
"normalized": false,
|
| 882 |
+
"special": true
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"id": 96,
|
| 886 |
+
"content": "[a]",
|
| 887 |
+
"single_word": false,
|
| 888 |
+
"lstrip": false,
|
| 889 |
+
"rstrip": false,
|
| 890 |
+
"normalized": false,
|
| 891 |
+
"special": true
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"id": 97,
|
| 895 |
+
"content": "[ɶ]",
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"lstrip": false,
|
| 898 |
+
"rstrip": false,
|
| 899 |
+
"normalized": false,
|
| 900 |
+
"special": true
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"id": 98,
|
| 904 |
+
"content": "[ɑ]",
|
| 905 |
+
"single_word": false,
|
| 906 |
+
"lstrip": false,
|
| 907 |
+
"rstrip": false,
|
| 908 |
+
"normalized": false,
|
| 909 |
+
"special": true
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"id": 99,
|
| 913 |
+
"content": "[ɒ]",
|
| 914 |
+
"single_word": false,
|
| 915 |
+
"lstrip": false,
|
| 916 |
+
"rstrip": false,
|
| 917 |
+
"normalized": false,
|
| 918 |
+
"special": true
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"id": 100,
|
| 922 |
+
"content": "[ä]",
|
| 923 |
+
"single_word": false,
|
| 924 |
+
"lstrip": false,
|
| 925 |
+
"rstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"special": true
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"id": 101,
|
| 931 |
+
"content": "[ë]",
|
| 932 |
+
"single_word": false,
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"rstrip": false,
|
| 935 |
+
"normalized": false,
|
| 936 |
+
"special": true
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"id": 102,
|
| 940 |
+
"content": "[ĩ]",
|
| 941 |
+
"single_word": false,
|
| 942 |
+
"lstrip": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"normalized": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"id": 103,
|
| 949 |
+
"content": "[áà]",
|
| 950 |
+
"single_word": false,
|
| 951 |
+
"lstrip": false,
|
| 952 |
+
"rstrip": false,
|
| 953 |
+
"normalized": false,
|
| 954 |
+
"special": true
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"id": 104,
|
| 958 |
+
"content": "[àá]",
|
| 959 |
+
"single_word": false,
|
| 960 |
+
"lstrip": false,
|
| 961 |
+
"rstrip": false,
|
| 962 |
+
"normalized": false,
|
| 963 |
+
"special": true
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"id": 105,
|
| 967 |
+
"content": "[áa]",
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"lstrip": false,
|
| 970 |
+
"rstrip": false,
|
| 971 |
+
"normalized": false,
|
| 972 |
+
"special": true
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"id": 106,
|
| 976 |
+
"content": "[aá]",
|
| 977 |
+
"single_word": false,
|
| 978 |
+
"lstrip": false,
|
| 979 |
+
"rstrip": false,
|
| 980 |
+
"normalized": false,
|
| 981 |
+
"special": true
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"id": 107,
|
| 985 |
+
"content": "[áá]",
|
| 986 |
+
"single_word": false,
|
| 987 |
+
"lstrip": false,
|
| 988 |
+
"rstrip": false,
|
| 989 |
+
"normalized": false,
|
| 990 |
+
"special": true
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"id": 108,
|
| 994 |
+
"content": "[əə́]",
|
| 995 |
+
"single_word": false,
|
| 996 |
+
"lstrip": false,
|
| 997 |
+
"rstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"special": true
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"id": 109,
|
| 1003 |
+
"content": "[ɛ́ɛ]",
|
| 1004 |
+
"single_word": false,
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"rstrip": false,
|
| 1007 |
+
"normalized": false,
|
| 1008 |
+
"special": true
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"id": 110,
|
| 1012 |
+
"content": "[ɛ́ɛ́]",
|
| 1013 |
+
"single_word": false,
|
| 1014 |
+
"lstrip": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"normalized": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"id": 111,
|
| 1021 |
+
"content": "[ə́ə́]",
|
| 1022 |
+
"single_word": false,
|
| 1023 |
+
"lstrip": false,
|
| 1024 |
+
"rstrip": false,
|
| 1025 |
+
"normalized": false,
|
| 1026 |
+
"special": true
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"id": 112,
|
| 1030 |
+
"content": "[ú]",
|
| 1031 |
+
"single_word": false,
|
| 1032 |
+
"lstrip": false,
|
| 1033 |
+
"rstrip": false,
|
| 1034 |
+
"normalized": false,
|
| 1035 |
+
"special": true
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"id": 113,
|
| 1039 |
+
"content": "[ó]",
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"lstrip": false,
|
| 1042 |
+
"rstrip": false,
|
| 1043 |
+
"normalized": false,
|
| 1044 |
+
"special": true
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"id": 114,
|
| 1048 |
+
"content": "[ɔ́]",
|
| 1049 |
+
"single_word": false,
|
| 1050 |
+
"lstrip": false,
|
| 1051 |
+
"rstrip": false,
|
| 1052 |
+
"normalized": false,
|
| 1053 |
+
"special": true
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"id": 115,
|
| 1057 |
+
"content": "[ɔ́ɔ́]",
|
| 1058 |
+
"single_word": false,
|
| 1059 |
+
"lstrip": false,
|
| 1060 |
+
"rstrip": false,
|
| 1061 |
+
"normalized": false,
|
| 1062 |
+
"special": true
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"id": 116,
|
| 1066 |
+
"content": "[á]",
|
| 1067 |
+
"single_word": false,
|
| 1068 |
+
"lstrip": false,
|
| 1069 |
+
"rstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"special": true
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"id": 117,
|
| 1075 |
+
"content": "[ə́]",
|
| 1076 |
+
"single_word": false,
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"rstrip": false,
|
| 1079 |
+
"normalized": false,
|
| 1080 |
+
"special": true
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"id": 118,
|
| 1084 |
+
"content": "[ɔɔ́]",
|
| 1085 |
+
"single_word": false,
|
| 1086 |
+
"lstrip": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"normalized": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"id": 119,
|
| 1093 |
+
"content": "[óó]",
|
| 1094 |
+
"single_word": false,
|
| 1095 |
+
"lstrip": false,
|
| 1096 |
+
"rstrip": false,
|
| 1097 |
+
"normalized": false,
|
| 1098 |
+
"special": true
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"id": 120,
|
| 1102 |
+
"content": "[í]",
|
| 1103 |
+
"single_word": false,
|
| 1104 |
+
"lstrip": false,
|
| 1105 |
+
"rstrip": false,
|
| 1106 |
+
"normalized": false,
|
| 1107 |
+
"special": true
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"id": 121,
|
| 1111 |
+
"content": "[Ɛ́]",
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"lstrip": false,
|
| 1114 |
+
"rstrip": false,
|
| 1115 |
+
"normalized": false,
|
| 1116 |
+
"special": true
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"id": 122,
|
| 1120 |
+
"content": "[d͡ʒ]",
|
| 1121 |
+
"single_word": false,
|
| 1122 |
+
"lstrip": false,
|
| 1123 |
+
"rstrip": false,
|
| 1124 |
+
"normalized": false,
|
| 1125 |
+
"special": true
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"id": 123,
|
| 1129 |
+
"content": "[...]",
|
| 1130 |
+
"single_word": false,
|
| 1131 |
+
"lstrip": false,
|
| 1132 |
+
"rstrip": false,
|
| 1133 |
+
"normalized": false,
|
| 1134 |
+
"special": true
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"id": 124,
|
| 1138 |
+
"content": "[-]",
|
| 1139 |
+
"single_word": false,
|
| 1140 |
+
"lstrip": false,
|
| 1141 |
+
"rstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"special": true
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"id": 125,
|
| 1147 |
+
"content": "[—]",
|
| 1148 |
+
"single_word": false,
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"rstrip": false,
|
| 1151 |
+
"normalized": false,
|
| 1152 |
+
"special": true
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"id": 126,
|
| 1156 |
+
"content": "[–]",
|
| 1157 |
+
"single_word": false,
|
| 1158 |
+
"lstrip": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"normalized": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"id": 127,
|
| 1165 |
+
"content": "[_]",
|
| 1166 |
+
"single_word": false,
|
| 1167 |
+
"lstrip": false,
|
| 1168 |
+
"rstrip": false,
|
| 1169 |
+
"normalized": false,
|
| 1170 |
+
"special": true
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"id": 128,
|
| 1174 |
+
"content": "[°]",
|
| 1175 |
+
"single_word": false,
|
| 1176 |
+
"lstrip": false,
|
| 1177 |
+
"rstrip": false,
|
| 1178 |
+
"normalized": false,
|
| 1179 |
+
"special": true
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"id": 129,
|
| 1183 |
+
"content": "[«]",
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"lstrip": false,
|
| 1186 |
+
"rstrip": false,
|
| 1187 |
+
"normalized": false,
|
| 1188 |
+
"special": true
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"id": 130,
|
| 1192 |
+
"content": "[»]",
|
| 1193 |
+
"single_word": false,
|
| 1194 |
+
"lstrip": false,
|
| 1195 |
+
"rstrip": false,
|
| 1196 |
+
"normalized": false,
|
| 1197 |
+
"special": true
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"id": 131,
|
| 1201 |
+
"content": "[(]",
|
| 1202 |
+
"single_word": false,
|
| 1203 |
+
"lstrip": false,
|
| 1204 |
+
"rstrip": false,
|
| 1205 |
+
"normalized": false,
|
| 1206 |
+
"special": true
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"id": 132,
|
| 1210 |
+
"content": "[)]",
|
| 1211 |
+
"single_word": false,
|
| 1212 |
+
"lstrip": false,
|
| 1213 |
+
"rstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"special": true
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"id": 133,
|
| 1219 |
+
"content": "[[]",
|
| 1220 |
+
"single_word": false,
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"rstrip": false,
|
| 1223 |
+
"normalized": false,
|
| 1224 |
+
"special": true
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"id": 134,
|
| 1228 |
+
"content": "[]]",
|
| 1229 |
+
"single_word": false,
|
| 1230 |
+
"lstrip": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"normalized": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"id": 135,
|
| 1237 |
+
"content": "[{]",
|
| 1238 |
+
"single_word": false,
|
| 1239 |
+
"lstrip": false,
|
| 1240 |
+
"rstrip": false,
|
| 1241 |
+
"normalized": false,
|
| 1242 |
+
"special": true
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"id": 136,
|
| 1246 |
+
"content": "[}]",
|
| 1247 |
+
"single_word": false,
|
| 1248 |
+
"lstrip": false,
|
| 1249 |
+
"rstrip": false,
|
| 1250 |
+
"normalized": false,
|
| 1251 |
+
"special": true
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"id": 137,
|
| 1255 |
+
"content": "[<]",
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"lstrip": false,
|
| 1258 |
+
"rstrip": false,
|
| 1259 |
+
"normalized": false,
|
| 1260 |
+
"special": true
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"id": 138,
|
| 1264 |
+
"content": "[>]",
|
| 1265 |
+
"single_word": false,
|
| 1266 |
+
"lstrip": false,
|
| 1267 |
+
"rstrip": false,
|
| 1268 |
+
"normalized": false,
|
| 1269 |
+
"special": true
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"id": 139,
|
| 1273 |
+
"content": "[&]",
|
| 1274 |
+
"single_word": false,
|
| 1275 |
+
"lstrip": false,
|
| 1276 |
+
"rstrip": false,
|
| 1277 |
+
"normalized": false,
|
| 1278 |
+
"special": true
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"id": 140,
|
| 1282 |
+
"content": "[*]",
|
| 1283 |
+
"single_word": false,
|
| 1284 |
+
"lstrip": false,
|
| 1285 |
+
"rstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"special": true
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"id": 141,
|
| 1291 |
+
"content": "[#]",
|
| 1292 |
+
"single_word": false,
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"rstrip": false,
|
| 1295 |
+
"normalized": false,
|
| 1296 |
+
"special": true
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"id": 142,
|
| 1300 |
+
"content": "[$]",
|
| 1301 |
+
"single_word": false,
|
| 1302 |
+
"lstrip": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"normalized": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"id": 143,
|
| 1309 |
+
"content": "[£]",
|
| 1310 |
+
"single_word": false,
|
| 1311 |
+
"lstrip": false,
|
| 1312 |
+
"rstrip": false,
|
| 1313 |
+
"normalized": false,
|
| 1314 |
+
"special": true
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"id": 144,
|
| 1318 |
+
"content": "[%]",
|
| 1319 |
+
"single_word": false,
|
| 1320 |
+
"lstrip": false,
|
| 1321 |
+
"rstrip": false,
|
| 1322 |
+
"normalized": false,
|
| 1323 |
+
"special": true
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"id": 145,
|
| 1327 |
+
"content": "[+]",
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"lstrip": false,
|
| 1330 |
+
"rstrip": false,
|
| 1331 |
+
"normalized": false,
|
| 1332 |
+
"special": true
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"id": 146,
|
| 1336 |
+
"content": "[=]",
|
| 1337 |
+
"single_word": false,
|
| 1338 |
+
"lstrip": false,
|
| 1339 |
+
"rstrip": false,
|
| 1340 |
+
"normalized": false,
|
| 1341 |
+
"special": true
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"id": 147,
|
| 1345 |
+
"content": "[|]",
|
| 1346 |
+
"single_word": false,
|
| 1347 |
+
"lstrip": false,
|
| 1348 |
+
"rstrip": false,
|
| 1349 |
+
"normalized": false,
|
| 1350 |
+
"special": true
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"id": 148,
|
| 1354 |
+
"content": "[/]",
|
| 1355 |
+
"single_word": false,
|
| 1356 |
+
"lstrip": false,
|
| 1357 |
+
"rstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"special": true
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"id": 149,
|
| 1363 |
+
"content": "[\\]",
|
| 1364 |
+
"single_word": false,
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"rstrip": false,
|
| 1367 |
+
"normalized": false,
|
| 1368 |
+
"special": true
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"id": 150,
|
| 1372 |
+
"content": "[@]",
|
| 1373 |
+
"single_word": false,
|
| 1374 |
+
"lstrip": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"normalized": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"id": 151,
|
| 1381 |
+
"content": "[www]",
|
| 1382 |
+
"single_word": false,
|
| 1383 |
+
"lstrip": false,
|
| 1384 |
+
"rstrip": false,
|
| 1385 |
+
"normalized": false,
|
| 1386 |
+
"special": true
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"id": 152,
|
| 1390 |
+
"content": "[,]",
|
| 1391 |
+
"single_word": false,
|
| 1392 |
+
"lstrip": false,
|
| 1393 |
+
"rstrip": false,
|
| 1394 |
+
"normalized": false,
|
| 1395 |
+
"special": true
|
| 1396 |
+
}
|
| 1397 |
+
],
|
| 1398 |
+
"normalizer": {
|
| 1399 |
+
"type": "Sequence",
|
| 1400 |
+
"normalizers": [
|
| 1401 |
+
{
|
| 1402 |
+
"type": "NFD"
|
| 1403 |
+
}
|
| 1404 |
+
]
|
| 1405 |
+
},
|
| 1406 |
+
"pre_tokenizer": {
|
| 1407 |
+
"type": "BertPreTokenizer"
|
| 1408 |
+
},
|
| 1409 |
+
"post_processor": {
|
| 1410 |
+
"type": "TemplateProcessing",
|
| 1411 |
+
"single": [
|
| 1412 |
+
{
|
| 1413 |
+
"SpecialToken": {
|
| 1414 |
+
"id": "[CLS]",
|
| 1415 |
+
"type_id": 0
|
| 1416 |
+
}
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"Sequence": {
|
| 1420 |
+
"id": "A",
|
| 1421 |
+
"type_id": 0
|
| 1422 |
+
}
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"SpecialToken": {
|
| 1426 |
+
"id": "[SEP]",
|
| 1427 |
+
"type_id": 0
|
| 1428 |
+
}
|
| 1429 |
+
}
|
| 1430 |
+
],
|
| 1431 |
+
"pair": [
|
| 1432 |
+
{
|
| 1433 |
+
"SpecialToken": {
|
| 1434 |
+
"id": "[CLS]",
|
| 1435 |
+
"type_id": 0
|
| 1436 |
+
}
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"Sequence": {
|
| 1440 |
+
"id": "A",
|
| 1441 |
+
"type_id": 0
|
| 1442 |
+
}
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"SpecialToken": {
|
| 1446 |
+
"id": "[SEP]",
|
| 1447 |
+
"type_id": 0
|
| 1448 |
+
}
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"Sequence": {
|
| 1452 |
+
"id": "B",
|
| 1453 |
+
"type_id": 1
|
| 1454 |
+
}
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"SpecialToken": {
|
| 1458 |
+
"id": "[SEP]",
|
| 1459 |
+
"type_id": 1
|
| 1460 |
+
}
|
| 1461 |
+
}
|
| 1462 |
+
],
|
| 1463 |
+
"special_tokens": {
|
| 1464 |
+
"[CLS]": {
|
| 1465 |
+
"id": "[CLS]",
|
| 1466 |
+
"ids": [
|
| 1467 |
+
2
|
| 1468 |
+
],
|
| 1469 |
+
"tokens": [
|
| 1470 |
+
"[CLS]"
|
| 1471 |
+
]
|
| 1472 |
+
},
|
| 1473 |
+
"[SEP]": {
|
| 1474 |
+
"id": "[SEP]",
|
| 1475 |
+
"ids": [
|
| 1476 |
+
3
|
| 1477 |
+
],
|
| 1478 |
+
"tokens": [
|
| 1479 |
+
"[SEP]"
|
| 1480 |
+
]
|
| 1481 |
+
}
|
| 1482 |
+
}
|
| 1483 |
+
},
|
| 1484 |
+
"decoder": {
|
| 1485 |
+
"type": "WordPiece",
|
| 1486 |
+
"prefix": "##",
|
| 1487 |
+
"cleanup": true
|
| 1488 |
+
},
|
| 1489 |
+
"model": {
|
| 1490 |
+
"type": "WordPiece",
|
| 1491 |
+
"unk_token": "[UNK]",
|
| 1492 |
+
"continuing_subword_prefix": "##",
|
| 1493 |
+
"max_input_chars_per_word": 100,
|
| 1494 |
+
"vocab": {
|
| 1495 |
+
"[UNK]": 0,
|
| 1496 |
+
"[PAD]": 1,
|
| 1497 |
+
"[CLS]": 2,
|
| 1498 |
+
"[SEP]": 3,
|
| 1499 |
+
"[MASK]": 4,
|
| 1500 |
+
"[p]": 5,
|
| 1501 |
+
"[b]": 6,
|
| 1502 |
+
"[t]": 7,
|
| 1503 |
+
"[d]": 8,
|
| 1504 |
+
"[ʈ]": 9,
|
| 1505 |
+
"[ɖ]": 10,
|
| 1506 |
+
"[c]": 11,
|
| 1507 |
+
"[ɟ]": 12,
|
| 1508 |
+
"[k]": 13,
|
| 1509 |
+
"[g]": 14,
|
| 1510 |
+
"[q]": 15,
|
| 1511 |
+
"[ɢ]": 16,
|
| 1512 |
+
"[ʔ]": 17,
|
| 1513 |
+
"[m]": 18,
|
| 1514 |
+
"[ɱ]": 19,
|
| 1515 |
+
"[n]": 20,
|
| 1516 |
+
"[ɳ]": 21,
|
| 1517 |
+
"[ɲ]": 22,
|
| 1518 |
+
"[ŋ]": 23,
|
| 1519 |
+
"[ɴ]": 24,
|
| 1520 |
+
"[ʙ]": 25,
|
| 1521 |
+
"[r]": 26,
|
| 1522 |
+
"[ʀ]": 27,
|
| 1523 |
+
"[ɾ]": 28,
|
| 1524 |
+
"[ɽ]": 29,
|
| 1525 |
+
"[ɸ]": 30,
|
| 1526 |
+
"[β]": 31,
|
| 1527 |
+
"[f]": 32,
|
| 1528 |
+
"[v]": 33,
|
| 1529 |
+
"[θ]": 34,
|
| 1530 |
+
"[ð]": 35,
|
| 1531 |
+
"[s]": 36,
|
| 1532 |
+
"[z]": 37,
|
| 1533 |
+
"[ʃ]": 38,
|
| 1534 |
+
"[ʒ]": 39,
|
| 1535 |
+
"[ʂ]": 40,
|
| 1536 |
+
"[ʐ]": 41,
|
| 1537 |
+
"[ç]": 42,
|
| 1538 |
+
"[ʝ]": 43,
|
| 1539 |
+
"[x]": 44,
|
| 1540 |
+
"[ɣ]": 45,
|
| 1541 |
+
"[χ]": 46,
|
| 1542 |
+
"[ʁ]": 47,
|
| 1543 |
+
"[ħ]": 48,
|
| 1544 |
+
"[ʕ]": 49,
|
| 1545 |
+
"[h]": 50,
|
| 1546 |
+
"[ɦ]": 51,
|
| 1547 |
+
"[ɬ]": 52,
|
| 1548 |
+
"[ɮ]": 53,
|
| 1549 |
+
"[ʋ]": 54,
|
| 1550 |
+
"[ɹ]": 55,
|
| 1551 |
+
"[ɻ]": 56,
|
| 1552 |
+
"[j]": 57,
|
| 1553 |
+
"[ɰ]": 58,
|
| 1554 |
+
"[l]": 59,
|
| 1555 |
+
"[ɭ]": 60,
|
| 1556 |
+
"[ʎ]": 61,
|
| 1557 |
+
"[ʟ]": 62,
|
| 1558 |
+
"[ƥ]": 63,
|
| 1559 |
+
"[ɓ]": 64,
|
| 1560 |
+
"[ƭ]": 65,
|
| 1561 |
+
"[ɗ]": 66,
|
| 1562 |
+
"[ƈ]": 67,
|
| 1563 |
+
"[ʄ]": 68,
|
| 1564 |
+
"[ƙ]": 69,
|
| 1565 |
+
"[ɠ]": 70,
|
| 1566 |
+
"[ʠ]": 71,
|
| 1567 |
+
"[ʛ]": 72,
|
| 1568 |
+
"[i]": 73,
|
| 1569 |
+
"[y]": 74,
|
| 1570 |
+
"[ɨ]": 75,
|
| 1571 |
+
"[ʉ]": 76,
|
| 1572 |
+
"[ɯ]": 77,
|
| 1573 |
+
"[u]": 78,
|
| 1574 |
+
"[ɪ]": 79,
|
| 1575 |
+
"[ʏ]": 80,
|
| 1576 |
+
"[ʊ]": 81,
|
| 1577 |
+
"[e]": 82,
|
| 1578 |
+
"[ø]": 83,
|
| 1579 |
+
"[ɘ]": 84,
|
| 1580 |
+
"[ɵ]": 85,
|
| 1581 |
+
"[ɤ]": 86,
|
| 1582 |
+
"[ə]": 87,
|
| 1583 |
+
"[ɛ]": 88,
|
| 1584 |
+
"[œ]": 89,
|
| 1585 |
+
"[ɜ]": 90,
|
| 1586 |
+
"[ɞ]": 91,
|
| 1587 |
+
"[ʌ]": 92,
|
| 1588 |
+
"[ɔ]": 93,
|
| 1589 |
+
"[æ]": 94,
|
| 1590 |
+
"[ɐ]": 95,
|
| 1591 |
+
"[a]": 96,
|
| 1592 |
+
"[ɶ]": 97,
|
| 1593 |
+
"[ɑ]": 98,
|
| 1594 |
+
"[ɒ]": 99,
|
| 1595 |
+
"[ä]": 100,
|
| 1596 |
+
"[ë]": 101,
|
| 1597 |
+
"[ĩ]": 102,
|
| 1598 |
+
"[áà]": 103,
|
| 1599 |
+
"[àá]": 104,
|
| 1600 |
+
"[áa]": 105,
|
| 1601 |
+
"[aá]": 106,
|
| 1602 |
+
"[áá]": 107,
|
| 1603 |
+
"[əə́]": 108,
|
| 1604 |
+
"[ɛ́ɛ]": 109,
|
| 1605 |
+
"[ɛ́ɛ́]": 110,
|
| 1606 |
+
"[ə́ə́]": 111,
|
| 1607 |
+
"[ú]": 112,
|
| 1608 |
+
"[ó]": 113,
|
| 1609 |
+
"[ɔ́]": 114,
|
| 1610 |
+
"[ɔ́ɔ́]": 115,
|
| 1611 |
+
"[á]": 116,
|
| 1612 |
+
"[ə́]": 117,
|
| 1613 |
+
"[ɔɔ́]": 118,
|
| 1614 |
+
"[óó]": 119,
|
| 1615 |
+
"[í]": 120,
|
| 1616 |
+
"[Ɛ́]": 121,
|
| 1617 |
+
"[d͡ʒ]": 122,
|
| 1618 |
+
"[...]": 123,
|
| 1619 |
+
"[-]": 124,
|
| 1620 |
+
"[—]": 125,
|
| 1621 |
+
"[–]": 126,
|
| 1622 |
+
"[_]": 127,
|
| 1623 |
+
"[°]": 128,
|
| 1624 |
+
"[«]": 129,
|
| 1625 |
+
"[»]": 130,
|
| 1626 |
+
"[(]": 131,
|
| 1627 |
+
"[)]": 132,
|
| 1628 |
+
"[[]": 133,
|
| 1629 |
+
"[]]": 134,
|
| 1630 |
+
"[{]": 135,
|
| 1631 |
+
"[}]": 136,
|
| 1632 |
+
"[<]": 137,
|
| 1633 |
+
"[>]": 138,
|
| 1634 |
+
"[&]": 139,
|
| 1635 |
+
"[*]": 140,
|
| 1636 |
+
"[#]": 141,
|
| 1637 |
+
"[$]": 142,
|
| 1638 |
+
"[£]": 143,
|
| 1639 |
+
"[%]": 144,
|
| 1640 |
+
"[+]": 145,
|
| 1641 |
+
"[=]": 146,
|
| 1642 |
+
"[|]": 147,
|
| 1643 |
+
"[/]": 148,
|
| 1644 |
+
"[\\]": 149,
|
| 1645 |
+
"[@]": 150,
|
| 1646 |
+
"[www]": 151,
|
| 1647 |
+
"[,]": 152
|
| 1648 |
+
}
|
| 1649 |
+
}
|
| 1650 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,1240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "[p]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "[b]",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"7": {
|
| 60 |
+
"content": "[t]",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"8": {
|
| 68 |
+
"content": "[d]",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"9": {
|
| 76 |
+
"content": "[ʈ]",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"10": {
|
| 84 |
+
"content": "[ɖ]",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"11": {
|
| 92 |
+
"content": "[c]",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"12": {
|
| 100 |
+
"content": "[ɟ]",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"13": {
|
| 108 |
+
"content": "[k]",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"14": {
|
| 116 |
+
"content": "[g]",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"15": {
|
| 124 |
+
"content": "[q]",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"16": {
|
| 132 |
+
"content": "[ɢ]",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"17": {
|
| 140 |
+
"content": "[ʔ]",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"18": {
|
| 148 |
+
"content": "[m]",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"19": {
|
| 156 |
+
"content": "[ɱ]",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"20": {
|
| 164 |
+
"content": "[n]",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"21": {
|
| 172 |
+
"content": "[ɳ]",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"22": {
|
| 180 |
+
"content": "[ɲ]",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"23": {
|
| 188 |
+
"content": "[ŋ]",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"24": {
|
| 196 |
+
"content": "[ɴ]",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"25": {
|
| 204 |
+
"content": "[ʙ]",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"26": {
|
| 212 |
+
"content": "[r]",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"27": {
|
| 220 |
+
"content": "[ʀ]",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"28": {
|
| 228 |
+
"content": "[ɾ]",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"29": {
|
| 236 |
+
"content": "[ɽ]",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"30": {
|
| 244 |
+
"content": "[ɸ]",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"31": {
|
| 252 |
+
"content": "[β]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32": {
|
| 260 |
+
"content": "[f]",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"33": {
|
| 268 |
+
"content": "[v]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"34": {
|
| 276 |
+
"content": "[θ]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"35": {
|
| 284 |
+
"content": "[ð]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"36": {
|
| 292 |
+
"content": "[s]",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"37": {
|
| 300 |
+
"content": "[z]",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"38": {
|
| 308 |
+
"content": "[ʃ]",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"39": {
|
| 316 |
+
"content": "[ʒ]",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"40": {
|
| 324 |
+
"content": "[ʂ]",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"41": {
|
| 332 |
+
"content": "[ʐ]",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"42": {
|
| 340 |
+
"content": "[ç]",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"43": {
|
| 348 |
+
"content": "[ʝ]",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"44": {
|
| 356 |
+
"content": "[x]",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"45": {
|
| 364 |
+
"content": "[ɣ]",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"46": {
|
| 372 |
+
"content": "[χ]",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"47": {
|
| 380 |
+
"content": "[ʁ]",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"48": {
|
| 388 |
+
"content": "[ħ]",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"49": {
|
| 396 |
+
"content": "[ʕ]",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"50": {
|
| 404 |
+
"content": "[h]",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"51": {
|
| 412 |
+
"content": "[ɦ]",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"52": {
|
| 420 |
+
"content": "[ɬ]",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"53": {
|
| 428 |
+
"content": "[ɮ]",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"54": {
|
| 436 |
+
"content": "[ʋ]",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"55": {
|
| 444 |
+
"content": "[ɹ]",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"56": {
|
| 452 |
+
"content": "[ɻ]",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"57": {
|
| 460 |
+
"content": "[j]",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"58": {
|
| 468 |
+
"content": "[ɰ]",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"59": {
|
| 476 |
+
"content": "[l]",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"60": {
|
| 484 |
+
"content": "[ɭ]",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"61": {
|
| 492 |
+
"content": "[ʎ]",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"62": {
|
| 500 |
+
"content": "[ʟ]",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"63": {
|
| 508 |
+
"content": "[ƥ]",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"64": {
|
| 516 |
+
"content": "[ɓ]",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"65": {
|
| 524 |
+
"content": "[ƭ]",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"66": {
|
| 532 |
+
"content": "[ɗ]",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"67": {
|
| 540 |
+
"content": "[ƈ]",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"68": {
|
| 548 |
+
"content": "[ʄ]",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"69": {
|
| 556 |
+
"content": "[ƙ]",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"70": {
|
| 564 |
+
"content": "[ɠ]",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"71": {
|
| 572 |
+
"content": "[ʠ]",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"72": {
|
| 580 |
+
"content": "[ʛ]",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"73": {
|
| 588 |
+
"content": "[i]",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"74": {
|
| 596 |
+
"content": "[y]",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"75": {
|
| 604 |
+
"content": "[ɨ]",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"76": {
|
| 612 |
+
"content": "[ʉ]",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"77": {
|
| 620 |
+
"content": "[ɯ]",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"78": {
|
| 628 |
+
"content": "[u]",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"79": {
|
| 636 |
+
"content": "[ɪ]",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"80": {
|
| 644 |
+
"content": "[ʏ]",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"81": {
|
| 652 |
+
"content": "[ʊ]",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"82": {
|
| 660 |
+
"content": "[e]",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"83": {
|
| 668 |
+
"content": "[ø]",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"84": {
|
| 676 |
+
"content": "[ɘ]",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"85": {
|
| 684 |
+
"content": "[ɵ]",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"86": {
|
| 692 |
+
"content": "[ɤ]",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"87": {
|
| 700 |
+
"content": "[ə]",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"88": {
|
| 708 |
+
"content": "[ɛ]",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"89": {
|
| 716 |
+
"content": "[œ]",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"90": {
|
| 724 |
+
"content": "[ɜ]",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"91": {
|
| 732 |
+
"content": "[ɞ]",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"92": {
|
| 740 |
+
"content": "[ʌ]",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"93": {
|
| 748 |
+
"content": "[ɔ]",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"94": {
|
| 756 |
+
"content": "[æ]",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"95": {
|
| 764 |
+
"content": "[ɐ]",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"96": {
|
| 772 |
+
"content": "[a]",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"97": {
|
| 780 |
+
"content": "[ɶ]",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"98": {
|
| 788 |
+
"content": "[ɑ]",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"99": {
|
| 796 |
+
"content": "[ɒ]",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"100": {
|
| 804 |
+
"content": "[ä]",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"101": {
|
| 812 |
+
"content": "[ë]",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"102": {
|
| 820 |
+
"content": "[ĩ]",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"103": {
|
| 828 |
+
"content": "[áà]",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"104": {
|
| 836 |
+
"content": "[àá]",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"105": {
|
| 844 |
+
"content": "[áa]",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"106": {
|
| 852 |
+
"content": "[aá]",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"107": {
|
| 860 |
+
"content": "[áá]",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"108": {
|
| 868 |
+
"content": "[əə́]",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"109": {
|
| 876 |
+
"content": "[ɛ́ɛ]",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"110": {
|
| 884 |
+
"content": "[ɛ́ɛ́]",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"111": {
|
| 892 |
+
"content": "[ə́ə́]",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"112": {
|
| 900 |
+
"content": "[ú]",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"113": {
|
| 908 |
+
"content": "[ó]",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"114": {
|
| 916 |
+
"content": "[ɔ́]",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"115": {
|
| 924 |
+
"content": "[ɔ́ɔ́]",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"116": {
|
| 932 |
+
"content": "[á]",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"117": {
|
| 940 |
+
"content": "[ə́]",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"118": {
|
| 948 |
+
"content": "[ɔɔ́]",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"119": {
|
| 956 |
+
"content": "[óó]",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"120": {
|
| 964 |
+
"content": "[í]",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"121": {
|
| 972 |
+
"content": "[Ɛ́]",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"122": {
|
| 980 |
+
"content": "[d͡ʒ]",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"123": {
|
| 988 |
+
"content": "[...]",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"124": {
|
| 996 |
+
"content": "[-]",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"125": {
|
| 1004 |
+
"content": "[—]",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"126": {
|
| 1012 |
+
"content": "[–]",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"127": {
|
| 1020 |
+
"content": "[_]",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128": {
|
| 1028 |
+
"content": "[°]",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"129": {
|
| 1036 |
+
"content": "[«]",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"130": {
|
| 1044 |
+
"content": "[»]",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"131": {
|
| 1052 |
+
"content": "[(]",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"132": {
|
| 1060 |
+
"content": "[)]",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"133": {
|
| 1068 |
+
"content": "[[]",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"134": {
|
| 1076 |
+
"content": "[]]",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"135": {
|
| 1084 |
+
"content": "[{]",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"136": {
|
| 1092 |
+
"content": "[}]",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"137": {
|
| 1100 |
+
"content": "[<]",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"138": {
|
| 1108 |
+
"content": "[>]",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"139": {
|
| 1116 |
+
"content": "[&]",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"140": {
|
| 1124 |
+
"content": "[*]",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"141": {
|
| 1132 |
+
"content": "[#]",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"142": {
|
| 1140 |
+
"content": "[$]",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"143": {
|
| 1148 |
+
"content": "[£]",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"144": {
|
| 1156 |
+
"content": "[%]",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"145": {
|
| 1164 |
+
"content": "[+]",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"146": {
|
| 1172 |
+
"content": "[=]",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"147": {
|
| 1180 |
+
"content": "[|]",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"148": {
|
| 1188 |
+
"content": "[/]",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"149": {
|
| 1196 |
+
"content": "[\\]",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"150": {
|
| 1204 |
+
"content": "[@]",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"151": {
|
| 1212 |
+
"content": "[www]",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"152": {
|
| 1220 |
+
"content": "[,]",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
}
|
| 1227 |
+
},
|
| 1228 |
+
"clean_up_tokenization_spaces": false,
|
| 1229 |
+
"cls_token": "[CLS]",
|
| 1230 |
+
"do_lower_case": true,
|
| 1231 |
+
"extra_special_tokens": {},
|
| 1232 |
+
"mask_token": "[MASK]",
|
| 1233 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 1234 |
+
"pad_token": "[PAD]",
|
| 1235 |
+
"sep_token": "[SEP]",
|
| 1236 |
+
"strip_accents": null,
|
| 1237 |
+
"tokenize_chinese_chars": true,
|
| 1238 |
+
"tokenizer_class": "BertTokenizer",
|
| 1239 |
+
"unk_token": "[UNK]"
|
| 1240 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cf7c6402aa582ce40d63eb851a7b1bc5208af8b6e561d440fd63591fbf01d77
|
| 3 |
+
size 5496
|
vocab.txt
ADDED
|
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[UNK]
|
| 2 |
+
[PAD]
|
| 3 |
+
[CLS]
|
| 4 |
+
[SEP]
|
| 5 |
+
[MASK]
|
| 6 |
+
[p]
|
| 7 |
+
[b]
|
| 8 |
+
[t]
|
| 9 |
+
[d]
|
| 10 |
+
[ʈ]
|
| 11 |
+
[ɖ]
|
| 12 |
+
[c]
|
| 13 |
+
[ɟ]
|
| 14 |
+
[k]
|
| 15 |
+
[g]
|
| 16 |
+
[q]
|
| 17 |
+
[ɢ]
|
| 18 |
+
[ʔ]
|
| 19 |
+
[m]
|
| 20 |
+
[ɱ]
|
| 21 |
+
[n]
|
| 22 |
+
[ɳ]
|
| 23 |
+
[ɲ]
|
| 24 |
+
[ŋ]
|
| 25 |
+
[ɴ]
|
| 26 |
+
[ʙ]
|
| 27 |
+
[r]
|
| 28 |
+
[ʀ]
|
| 29 |
+
[ɾ]
|
| 30 |
+
[ɽ]
|
| 31 |
+
[ɸ]
|
| 32 |
+
[β]
|
| 33 |
+
[f]
|
| 34 |
+
[v]
|
| 35 |
+
[θ]
|
| 36 |
+
[ð]
|
| 37 |
+
[s]
|
| 38 |
+
[z]
|
| 39 |
+
[ʃ]
|
| 40 |
+
[ʒ]
|
| 41 |
+
[ʂ]
|
| 42 |
+
[ʐ]
|
| 43 |
+
[ç]
|
| 44 |
+
[ʝ]
|
| 45 |
+
[x]
|
| 46 |
+
[ɣ]
|
| 47 |
+
[χ]
|
| 48 |
+
[ʁ]
|
| 49 |
+
[ħ]
|
| 50 |
+
[ʕ]
|
| 51 |
+
[h]
|
| 52 |
+
[ɦ]
|
| 53 |
+
[ɬ]
|
| 54 |
+
[ɮ]
|
| 55 |
+
[ʋ]
|
| 56 |
+
[ɹ]
|
| 57 |
+
[ɻ]
|
| 58 |
+
[j]
|
| 59 |
+
[ɰ]
|
| 60 |
+
[l]
|
| 61 |
+
[ɭ]
|
| 62 |
+
[ʎ]
|
| 63 |
+
[ʟ]
|
| 64 |
+
[ƥ]
|
| 65 |
+
[ɓ]
|
| 66 |
+
[ƭ]
|
| 67 |
+
[ɗ]
|
| 68 |
+
[ƈ]
|
| 69 |
+
[ʄ]
|
| 70 |
+
[ƙ]
|
| 71 |
+
[ɠ]
|
| 72 |
+
[ʠ]
|
| 73 |
+
[ʛ]
|
| 74 |
+
[i]
|
| 75 |
+
[y]
|
| 76 |
+
[ɨ]
|
| 77 |
+
[ʉ]
|
| 78 |
+
[ɯ]
|
| 79 |
+
[u]
|
| 80 |
+
[ɪ]
|
| 81 |
+
[ʏ]
|
| 82 |
+
[ʊ]
|
| 83 |
+
[e]
|
| 84 |
+
[ø]
|
| 85 |
+
[ɘ]
|
| 86 |
+
[ɵ]
|
| 87 |
+
[ɤ]
|
| 88 |
+
[ə]
|
| 89 |
+
[ɛ]
|
| 90 |
+
[œ]
|
| 91 |
+
[ɜ]
|
| 92 |
+
[ɞ]
|
| 93 |
+
[ʌ]
|
| 94 |
+
[ɔ]
|
| 95 |
+
[æ]
|
| 96 |
+
[ɐ]
|
| 97 |
+
[a]
|
| 98 |
+
[ɶ]
|
| 99 |
+
[ɑ]
|
| 100 |
+
[ɒ]
|
| 101 |
+
[ä]
|
| 102 |
+
[ë]
|
| 103 |
+
[ĩ]
|
| 104 |
+
[áà]
|
| 105 |
+
[àá]
|
| 106 |
+
[áa]
|
| 107 |
+
[aá]
|
| 108 |
+
[áá]
|
| 109 |
+
[əə́]
|
| 110 |
+
[ɛ́ɛ]
|
| 111 |
+
[ɛ́ɛ́]
|
| 112 |
+
[ə́ə́]
|
| 113 |
+
[ú]
|
| 114 |
+
[ó]
|
| 115 |
+
[ɔ́]
|
| 116 |
+
[ɔ́ɔ́]
|
| 117 |
+
[á]
|
| 118 |
+
[ə́]
|
| 119 |
+
[ɔɔ́]
|
| 120 |
+
[óó]
|
| 121 |
+
[í]
|
| 122 |
+
[Ɛ́]
|
| 123 |
+
[d͡ʒ]
|
| 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 |
+
[www]
|
| 153 |
+
[,]
|