Upload 10 files
Browse files- config.json +110 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +213 -0
- training_args.bin +3 -0
- vocab.json +708 -0
config.json
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nguyenvulebinh/wav2vec2-base-vietnamese-250h",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"adapter_attn_dim": null,
|
| 5 |
+
"adapter_kernel_size": 3,
|
| 6 |
+
"adapter_stride": 2,
|
| 7 |
+
"add_adapter": false,
|
| 8 |
+
"apply_spec_augment": true,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"Wav2Vec2ForCTC"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 256,
|
| 16 |
+
"contrastive_logits_temperature": 0.1,
|
| 17 |
+
"conv_bias": false,
|
| 18 |
+
"conv_dim": [
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512,
|
| 25 |
+
512
|
| 26 |
+
],
|
| 27 |
+
"conv_kernel": [
|
| 28 |
+
10,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
3,
|
| 33 |
+
2,
|
| 34 |
+
2
|
| 35 |
+
],
|
| 36 |
+
"conv_stride": [
|
| 37 |
+
5,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2,
|
| 43 |
+
2
|
| 44 |
+
],
|
| 45 |
+
"ctc_loss_reduction": "mean",
|
| 46 |
+
"ctc_zero_infinity": false,
|
| 47 |
+
"diversity_loss_weight": 0.1,
|
| 48 |
+
"do_stable_layer_norm": false,
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_dropout": 0.0,
|
| 52 |
+
"feat_extract_norm": "group",
|
| 53 |
+
"feat_proj_dropout": 0.1,
|
| 54 |
+
"feat_quantizer_dropout": 0.0,
|
| 55 |
+
"final_dropout": 0.1,
|
| 56 |
+
"hidden_act": "gelu",
|
| 57 |
+
"hidden_dropout": 0.1,
|
| 58 |
+
"hidden_dropout_prob": 0.1,
|
| 59 |
+
"hidden_size": 768,
|
| 60 |
+
"initializer_range": 0.02,
|
| 61 |
+
"intermediate_size": 3072,
|
| 62 |
+
"layer_norm_eps": 1e-05,
|
| 63 |
+
"layerdrop": 0.1,
|
| 64 |
+
"mask_feature_length": 10,
|
| 65 |
+
"mask_feature_min_masks": 0,
|
| 66 |
+
"mask_feature_prob": 0.0,
|
| 67 |
+
"mask_time_length": 10,
|
| 68 |
+
"mask_time_min_masks": 2,
|
| 69 |
+
"mask_time_prob": 0.05,
|
| 70 |
+
"model_type": "wav2vec2",
|
| 71 |
+
"num_adapter_layers": 3,
|
| 72 |
+
"num_attention_heads": 12,
|
| 73 |
+
"num_codevector_groups": 2,
|
| 74 |
+
"num_codevectors_per_group": 320,
|
| 75 |
+
"num_conv_pos_embedding_groups": 16,
|
| 76 |
+
"num_conv_pos_embeddings": 128,
|
| 77 |
+
"num_feat_extract_layers": 7,
|
| 78 |
+
"num_hidden_layers": 12,
|
| 79 |
+
"num_negatives": 100,
|
| 80 |
+
"output_hidden_size": 768,
|
| 81 |
+
"pad_token_id": 109,
|
| 82 |
+
"proj_codevector_dim": 256,
|
| 83 |
+
"tdnn_dilation": [
|
| 84 |
+
1,
|
| 85 |
+
2,
|
| 86 |
+
3,
|
| 87 |
+
1,
|
| 88 |
+
1
|
| 89 |
+
],
|
| 90 |
+
"tdnn_dim": [
|
| 91 |
+
512,
|
| 92 |
+
512,
|
| 93 |
+
512,
|
| 94 |
+
512,
|
| 95 |
+
1500
|
| 96 |
+
],
|
| 97 |
+
"tdnn_kernel": [
|
| 98 |
+
5,
|
| 99 |
+
3,
|
| 100 |
+
3,
|
| 101 |
+
1,
|
| 102 |
+
1
|
| 103 |
+
],
|
| 104 |
+
"torch_dtype": "float32",
|
| 105 |
+
"transformers_version": "4.44.0",
|
| 106 |
+
"use_weighted_layer_sum": false,
|
| 107 |
+
"vocab_size": 110,
|
| 108 |
+
"xvector_output_dim": 512,
|
| 109 |
+
"gradient_checkpointing": true
|
| 110 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe41656cdc386b0ad40fbf1ac4d221324f6472acb11f8117a077199813773973
|
| 3 |
+
size 377851056
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdc142be3229822b505829e6446275f4bd52020b04bb24ae8ec223e8f90fc6d4
|
| 3 |
+
size 722217338
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"return_attention_mask": false,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acf088c2f45c72065940245599d63b70ca7bffbcee4298ad39bb5263487c70b0
|
| 3 |
+
size 377899102
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bdb89cb77fa8ff8ca67b00d1272465f68fdd8d8c1ee9a643b39d80c0ea6f39f
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f57e63648be46ceeb4d55fb75ad13f4bfad738df31db0d7d2cd668bb958620b5
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.37462568283081055,
|
| 3 |
+
"best_model_checkpoint": "./wav2vec2-base-demo/checkpoint-1000",
|
| 4 |
+
"epoch": 18.71101871101871,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 2.079002079002079,
|
| 13 |
+
"grad_norm": 1.480198621749878,
|
| 14 |
+
"learning_rate": 2.46e-05,
|
| 15 |
+
"loss": 0.9611,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 2.079002079002079,
|
| 20 |
+
"eval_cer": 0.11971565962784864,
|
| 21 |
+
"eval_loss": 0.4033341407775879,
|
| 22 |
+
"eval_mer": 0.2592487677751969,
|
| 23 |
+
"eval_runtime": 32.5187,
|
| 24 |
+
"eval_samples_per_second": 47.265,
|
| 25 |
+
"eval_steps_per_second": 5.935,
|
| 26 |
+
"eval_wer": 0.2618448157473106,
|
| 27 |
+
"eval_wil": 0.4233489392452203,
|
| 28 |
+
"eval_wip": 0.5766510607547797,
|
| 29 |
+
"step": 500
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 4.158004158004158,
|
| 33 |
+
"grad_norm": 1.976112961769104,
|
| 34 |
+
"learning_rate": 4.92e-05,
|
| 35 |
+
"loss": 0.55,
|
| 36 |
+
"step": 1000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 4.158004158004158,
|
| 40 |
+
"eval_cer": 0.08507909958882152,
|
| 41 |
+
"eval_loss": 0.37462568283081055,
|
| 42 |
+
"eval_mer": 0.1971511264967936,
|
| 43 |
+
"eval_runtime": 32.245,
|
| 44 |
+
"eval_samples_per_second": 47.666,
|
| 45 |
+
"eval_steps_per_second": 5.985,
|
| 46 |
+
"eval_wer": 0.19878690775921262,
|
| 47 |
+
"eval_wil": 0.33487393467226145,
|
| 48 |
+
"eval_wip": 0.6651260653277385,
|
| 49 |
+
"step": 1000
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 6.237006237006237,
|
| 53 |
+
"grad_norm": 0.5409166216850281,
|
| 54 |
+
"learning_rate": 4.373684210526316e-05,
|
| 55 |
+
"loss": 0.4558,
|
| 56 |
+
"step": 1500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 6.237006237006237,
|
| 60 |
+
"eval_cer": 0.07582409924036518,
|
| 61 |
+
"eval_loss": 0.4071575403213501,
|
| 62 |
+
"eval_mer": 0.19740067263295902,
|
| 63 |
+
"eval_runtime": 32.4791,
|
| 64 |
+
"eval_samples_per_second": 47.323,
|
| 65 |
+
"eval_steps_per_second": 5.942,
|
| 66 |
+
"eval_wer": 0.1981574731059739,
|
| 67 |
+
"eval_wil": 0.328165644386755,
|
| 68 |
+
"eval_wip": 0.671834355613245,
|
| 69 |
+
"step": 1500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 8.316008316008316,
|
| 73 |
+
"grad_norm": 0.0,
|
| 74 |
+
"learning_rate": 3.726315789473684e-05,
|
| 75 |
+
"loss": 0.7148,
|
| 76 |
+
"step": 2000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 8.316008316008316,
|
| 80 |
+
"eval_cer": 0.08355982995330685,
|
| 81 |
+
"eval_loss": 0.5936842560768127,
|
| 82 |
+
"eval_mer": 0.23157714481420172,
|
| 83 |
+
"eval_runtime": 32.384,
|
| 84 |
+
"eval_samples_per_second": 47.462,
|
| 85 |
+
"eval_steps_per_second": 5.96,
|
| 86 |
+
"eval_wer": 0.2321469443808652,
|
| 87 |
+
"eval_wil": 0.36899346973472724,
|
| 88 |
+
"eval_wip": 0.6310065302652728,
|
| 89 |
+
"step": 2000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 10.395010395010395,
|
| 93 |
+
"grad_norm": 0.0,
|
| 94 |
+
"learning_rate": 3.075e-05,
|
| 95 |
+
"loss": 0.7728,
|
| 96 |
+
"step": 2500
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 10.395010395010395,
|
| 100 |
+
"eval_cer": 0.08300229981183357,
|
| 101 |
+
"eval_loss": 0.5987456440925598,
|
| 102 |
+
"eval_mer": 0.22851272685766466,
|
| 103 |
+
"eval_runtime": 32.4007,
|
| 104 |
+
"eval_samples_per_second": 47.437,
|
| 105 |
+
"eval_steps_per_second": 5.957,
|
| 106 |
+
"eval_wer": 0.22911421377889676,
|
| 107 |
+
"eval_wil": 0.36543173415209407,
|
| 108 |
+
"eval_wip": 0.6345682658479059,
|
| 109 |
+
"step": 2500
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 12.474012474012474,
|
| 113 |
+
"grad_norm": 0.0,
|
| 114 |
+
"learning_rate": 2.4263157894736844e-05,
|
| 115 |
+
"loss": 0.7776,
|
| 116 |
+
"step": 3000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 12.474012474012474,
|
| 120 |
+
"eval_cer": 0.08303017631890725,
|
| 121 |
+
"eval_loss": 0.5985206961631775,
|
| 122 |
+
"eval_mer": 0.22846869470920608,
|
| 123 |
+
"eval_runtime": 32.4117,
|
| 124 |
+
"eval_samples_per_second": 47.421,
|
| 125 |
+
"eval_steps_per_second": 5.955,
|
| 126 |
+
"eval_wer": 0.22905699244678415,
|
| 127 |
+
"eval_wil": 0.36539322178541034,
|
| 128 |
+
"eval_wip": 0.6346067782145897,
|
| 129 |
+
"step": 3000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 14.553014553014552,
|
| 133 |
+
"grad_norm": 0.0,
|
| 134 |
+
"learning_rate": 1.7776315789473686e-05,
|
| 135 |
+
"loss": 0.7775,
|
| 136 |
+
"step": 3500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 14.553014553014552,
|
| 140 |
+
"eval_cer": 0.08296048505122308,
|
| 141 |
+
"eval_loss": 0.5982343554496765,
|
| 142 |
+
"eval_mer": 0.22846869470920608,
|
| 143 |
+
"eval_runtime": 32.9767,
|
| 144 |
+
"eval_samples_per_second": 46.609,
|
| 145 |
+
"eval_steps_per_second": 5.853,
|
| 146 |
+
"eval_wer": 0.22905699244678415,
|
| 147 |
+
"eval_wil": 0.36539322178541034,
|
| 148 |
+
"eval_wip": 0.6346067782145897,
|
| 149 |
+
"step": 3500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 16.632016632016633,
|
| 153 |
+
"grad_norm": 0.0,
|
| 154 |
+
"learning_rate": 1.1315789473684212e-05,
|
| 155 |
+
"loss": 0.7767,
|
| 156 |
+
"step": 4000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 16.632016632016633,
|
| 160 |
+
"eval_cer": 0.08294654679768625,
|
| 161 |
+
"eval_loss": 0.5979084372520447,
|
| 162 |
+
"eval_mer": 0.22846869470920608,
|
| 163 |
+
"eval_runtime": 32.5362,
|
| 164 |
+
"eval_samples_per_second": 47.24,
|
| 165 |
+
"eval_steps_per_second": 5.932,
|
| 166 |
+
"eval_wer": 0.22905699244678415,
|
| 167 |
+
"eval_wil": 0.36543173415209407,
|
| 168 |
+
"eval_wip": 0.6345682658479059,
|
| 169 |
+
"step": 4000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 18.71101871101871,
|
| 173 |
+
"grad_norm": 0.0,
|
| 174 |
+
"learning_rate": 4.842105263157895e-06,
|
| 175 |
+
"loss": 0.7749,
|
| 176 |
+
"step": 4500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 18.71101871101871,
|
| 180 |
+
"eval_cer": 0.08301623806537041,
|
| 181 |
+
"eval_loss": 0.597719132900238,
|
| 182 |
+
"eval_mer": 0.22858284344500884,
|
| 183 |
+
"eval_runtime": 32.5471,
|
| 184 |
+
"eval_samples_per_second": 47.224,
|
| 185 |
+
"eval_steps_per_second": 5.93,
|
| 186 |
+
"eval_wer": 0.22917143511100938,
|
| 187 |
+
"eval_wil": 0.36558098915718085,
|
| 188 |
+
"eval_wip": 0.6344190108428192,
|
| 189 |
+
"step": 4500
|
| 190 |
+
}
|
| 191 |
+
],
|
| 192 |
+
"logging_steps": 500,
|
| 193 |
+
"max_steps": 4800,
|
| 194 |
+
"num_input_tokens_seen": 0,
|
| 195 |
+
"num_train_epochs": 20,
|
| 196 |
+
"save_steps": 500,
|
| 197 |
+
"stateful_callbacks": {
|
| 198 |
+
"TrainerControl": {
|
| 199 |
+
"args": {
|
| 200 |
+
"should_epoch_stop": false,
|
| 201 |
+
"should_evaluate": false,
|
| 202 |
+
"should_log": false,
|
| 203 |
+
"should_save": true,
|
| 204 |
+
"should_training_stop": false
|
| 205 |
+
},
|
| 206 |
+
"attributes": {}
|
| 207 |
+
}
|
| 208 |
+
},
|
| 209 |
+
"total_flos": 5.612324111737915e+18,
|
| 210 |
+
"train_batch_size": 16,
|
| 211 |
+
"trial_name": null,
|
| 212 |
+
"trial_params": null
|
| 213 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58c47be2507fdeb4279d3a6031bf88f8479b4ef8aab90e9a722a7b0723dea54d
|
| 3 |
+
size 5176
|
vocab.json
ADDED
|
@@ -0,0 +1,708 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 0,
|
| 3 |
+
"<s>": 1,
|
| 4 |
+
"</s>": 2,
|
| 5 |
+
"<unk>": 3,
|
| 6 |
+
"|": 4,
|
| 7 |
+
"a": 5,
|
| 8 |
+
"á": 6,
|
| 9 |
+
"à": 7,
|
| 10 |
+
"ả": 8,
|
| 11 |
+
"ã": 9,
|
| 12 |
+
"ạ": 10,
|
| 13 |
+
"e": 11,
|
| 14 |
+
"é": 12,
|
| 15 |
+
"è": 13,
|
| 16 |
+
"ẻ": 14,
|
| 17 |
+
"ẽ": 15,
|
| 18 |
+
"ẹ": 16,
|
| 19 |
+
"ê": 17,
|
| 20 |
+
"ế": 18,
|
| 21 |
+
"ề": 19,
|
| 22 |
+
"ể": 20,
|
| 23 |
+
"ễ": 21,
|
| 24 |
+
"ệ": 22,
|
| 25 |
+
"i": 23,
|
| 26 |
+
"í": 24,
|
| 27 |
+
"ì": 25,
|
| 28 |
+
"ỉ": 26,
|
| 29 |
+
"ĩ": 27,
|
| 30 |
+
"ị": 28,
|
| 31 |
+
"o": 29,
|
| 32 |
+
"ó": 30,
|
| 33 |
+
"ò": 31,
|
| 34 |
+
"ỏ": 32,
|
| 35 |
+
"õ": 33,
|
| 36 |
+
"ọ": 34,
|
| 37 |
+
"ơ": 35,
|
| 38 |
+
"ớ": 36,
|
| 39 |
+
"ờ": 37,
|
| 40 |
+
"ở": 38,
|
| 41 |
+
"ỡ": 39,
|
| 42 |
+
"ợ": 40,
|
| 43 |
+
"ô": 41,
|
| 44 |
+
"ố": 42,
|
| 45 |
+
"ồ": 43,
|
| 46 |
+
"ổ": 44,
|
| 47 |
+
"ỗ": 45,
|
| 48 |
+
"ộ": 46,
|
| 49 |
+
"u": 47,
|
| 50 |
+
"ú": 48,
|
| 51 |
+
"ù": 49,
|
| 52 |
+
"ủ": 50,
|
| 53 |
+
"ũ": 51,
|
| 54 |
+
"ụ": 52,
|
| 55 |
+
"ư": 53,
|
| 56 |
+
"ứ": 54,
|
| 57 |
+
"ừ": 55,
|
| 58 |
+
"ử": 56,
|
| 59 |
+
"ữ": 57,
|
| 60 |
+
"ự": 58,
|
| 61 |
+
"y": 59,
|
| 62 |
+
"ỳ": 60,
|
| 63 |
+
"ý": 61,
|
| 64 |
+
"ỷ": 62,
|
| 65 |
+
"ỹ": 63,
|
| 66 |
+
"ỵ": 64,
|
| 67 |
+
"ă": 65,
|
| 68 |
+
"ắ": 66,
|
| 69 |
+
"ằ": 67,
|
| 70 |
+
"ẳ": 68,
|
| 71 |
+
"ẵ": 69,
|
| 72 |
+
"ặ": 70,
|
| 73 |
+
"â": 71,
|
| 74 |
+
"ấ": 72,
|
| 75 |
+
"ầ": 73,
|
| 76 |
+
"ẩ": 74,
|
| 77 |
+
"ẫ": 75,
|
| 78 |
+
"ậ": 76,
|
| 79 |
+
"đ": 77,
|
| 80 |
+
"q": 78,
|
| 81 |
+
"w": 79,
|
| 82 |
+
"r": 80,
|
| 83 |
+
"t": 81,
|
| 84 |
+
"p": 82,
|
| 85 |
+
"s": 83,
|
| 86 |
+
"d": 84,
|
| 87 |
+
"f": 85,
|
| 88 |
+
"g": 86,
|
| 89 |
+
"h": 87,
|
| 90 |
+
"j": 88,
|
| 91 |
+
"k": 89,
|
| 92 |
+
"l": 90,
|
| 93 |
+
"z": 91,
|
| 94 |
+
"x": 92,
|
| 95 |
+
"c": 93,
|
| 96 |
+
"v": 94,
|
| 97 |
+
"b": 95,
|
| 98 |
+
"n": 96,
|
| 99 |
+
"m": 97,
|
| 100 |
+
"th": 98,
|
| 101 |
+
"ch": 99,
|
| 102 |
+
"kh": 100,
|
| 103 |
+
"ph": 101,
|
| 104 |
+
"nh": 102,
|
| 105 |
+
"gh": 103,
|
| 106 |
+
"qu": 104,
|
| 107 |
+
"ng": 105,
|
| 108 |
+
"ngh": 106,
|
| 109 |
+
"tr": 107,
|
| 110 |
+
"ác": 108,
|
| 111 |
+
"ạc": 109,
|
| 112 |
+
"ai": 110,
|
| 113 |
+
"ái": 111,
|
| 114 |
+
"ài": 112,
|
| 115 |
+
"ải": 113,
|
| 116 |
+
"ãi": 114,
|
| 117 |
+
"ại": 115,
|
| 118 |
+
"am": 116,
|
| 119 |
+
"ám": 117,
|
| 120 |
+
"àm": 118,
|
| 121 |
+
"ảm": 119,
|
| 122 |
+
"ãm": 120,
|
| 123 |
+
"ạm": 121,
|
| 124 |
+
"an": 122,
|
| 125 |
+
"án": 123,
|
| 126 |
+
"àn": 124,
|
| 127 |
+
"ản": 125,
|
| 128 |
+
"ãn": 126,
|
| 129 |
+
"ạn": 127,
|
| 130 |
+
"ao": 128,
|
| 131 |
+
"áo": 129,
|
| 132 |
+
"ào": 130,
|
| 133 |
+
"ảo": 131,
|
| 134 |
+
"ão": 132,
|
| 135 |
+
"ạo": 133,
|
| 136 |
+
"au": 134,
|
| 137 |
+
"áu": 135,
|
| 138 |
+
"àu": 136,
|
| 139 |
+
"ảu": 137,
|
| 140 |
+
"ãu": 138,
|
| 141 |
+
"ạu": 139,
|
| 142 |
+
"áp": 140,
|
| 143 |
+
"ạp": 141,
|
| 144 |
+
"át": 142,
|
| 145 |
+
"ạt": 143,
|
| 146 |
+
"ay": 144,
|
| 147 |
+
"áy": 145,
|
| 148 |
+
"ày": 146,
|
| 149 |
+
"ảy": 147,
|
| 150 |
+
"ãy": 148,
|
| 151 |
+
"ạy": 149,
|
| 152 |
+
"ắc": 150,
|
| 153 |
+
"ặc": 151,
|
| 154 |
+
"ăm": 152,
|
| 155 |
+
"ằm": 153,
|
| 156 |
+
"ắm": 154,
|
| 157 |
+
"ẳm": 155,
|
| 158 |
+
"ẵm": 156,
|
| 159 |
+
"ặm": 157,
|
| 160 |
+
"ăn": 158,
|
| 161 |
+
"ắn": 159,
|
| 162 |
+
"ằn": 160,
|
| 163 |
+
"ẳn": 161,
|
| 164 |
+
"ẵn": 162,
|
| 165 |
+
"ặn": 163,
|
| 166 |
+
"ắp": 164,
|
| 167 |
+
"ặp": 165,
|
| 168 |
+
"ắt": 166,
|
| 169 |
+
"ặt": 167,
|
| 170 |
+
"ấc": 168,
|
| 171 |
+
"ậc": 169,
|
| 172 |
+
"âm": 170,
|
| 173 |
+
"ấm": 171,
|
| 174 |
+
"ầm": 172,
|
| 175 |
+
"ẩm": 173,
|
| 176 |
+
"ẫm": 174,
|
| 177 |
+
"ậm": 175,
|
| 178 |
+
"ân": 176,
|
| 179 |
+
"ấn": 177,
|
| 180 |
+
"ần": 178,
|
| 181 |
+
"ẩn": 179,
|
| 182 |
+
"ẫn": 180,
|
| 183 |
+
"ận": 181,
|
| 184 |
+
"ấp": 182,
|
| 185 |
+
"ập": 183,
|
| 186 |
+
"ất": 184,
|
| 187 |
+
"ật": 185,
|
| 188 |
+
"âu": 186,
|
| 189 |
+
"ấu": 187,
|
| 190 |
+
"ầu": 188,
|
| 191 |
+
"ẩu": 189,
|
| 192 |
+
"ẫu": 190,
|
| 193 |
+
"ậu": 191,
|
| 194 |
+
"ây": 192,
|
| 195 |
+
"ấy": 193,
|
| 196 |
+
"ầy": 194,
|
| 197 |
+
"ẩy": 195,
|
| 198 |
+
"ẫy": 196,
|
| 199 |
+
"ậy": 197,
|
| 200 |
+
"éc": 198,
|
| 201 |
+
"ẹc": 199,
|
| 202 |
+
"em": 200,
|
| 203 |
+
"ém": 201,
|
| 204 |
+
"èm": 202,
|
| 205 |
+
"ẻm": 203,
|
| 206 |
+
"ẽm": 204,
|
| 207 |
+
"ẹm": 205,
|
| 208 |
+
"en": 206,
|
| 209 |
+
"én": 207,
|
| 210 |
+
"èn": 208,
|
| 211 |
+
"ẻn": 209,
|
| 212 |
+
"ẽn": 210,
|
| 213 |
+
"ẹn": 211,
|
| 214 |
+
"eo": 212,
|
| 215 |
+
"éo": 213,
|
| 216 |
+
"èo": 214,
|
| 217 |
+
"ẻo": 215,
|
| 218 |
+
"ẽo": 216,
|
| 219 |
+
"ẹo": 217,
|
| 220 |
+
"ép": 218,
|
| 221 |
+
"ẹp": 219,
|
| 222 |
+
"ét": 220,
|
| 223 |
+
"ẹt": 221,
|
| 224 |
+
"êm": 222,
|
| 225 |
+
"ếm": 223,
|
| 226 |
+
"ềm": 224,
|
| 227 |
+
"ễm": 225,
|
| 228 |
+
"ệm": 226,
|
| 229 |
+
"ên": 227,
|
| 230 |
+
"ến": 228,
|
| 231 |
+
"ền": 229,
|
| 232 |
+
"ển": 230,
|
| 233 |
+
"ện": 231,
|
| 234 |
+
"ếp": 232,
|
| 235 |
+
"ệp": 233,
|
| 236 |
+
"ết": 234,
|
| 237 |
+
"ệt": 235,
|
| 238 |
+
"êu": 236,
|
| 239 |
+
"ếu": 237,
|
| 240 |
+
"ều": 238,
|
| 241 |
+
"ểu": 239,
|
| 242 |
+
"ễu": 240,
|
| 243 |
+
"ệu": 241,
|
| 244 |
+
"ia": 242,
|
| 245 |
+
"ía": 243,
|
| 246 |
+
"ìa": 244,
|
| 247 |
+
"ỉa": 245,
|
| 248 |
+
"ĩa": 246,
|
| 249 |
+
"ịa": 247,
|
| 250 |
+
"im": 248,
|
| 251 |
+
"ím": 249,
|
| 252 |
+
"ìm": 250,
|
| 253 |
+
"ỉm": 251,
|
| 254 |
+
"ĩm": 252,
|
| 255 |
+
"ịm": 253,
|
| 256 |
+
"in": 254,
|
| 257 |
+
"ín": 255,
|
| 258 |
+
"ìn": 256,
|
| 259 |
+
"ỉn": 257,
|
| 260 |
+
"ịn": 258,
|
| 261 |
+
"íp": 259,
|
| 262 |
+
"ịp": 260,
|
| 263 |
+
"ít": 261,
|
| 264 |
+
"ịt": 262,
|
| 265 |
+
"iu": 263,
|
| 266 |
+
"íu": 264,
|
| 267 |
+
"ìu": 265,
|
| 268 |
+
"ỉu": 266,
|
| 269 |
+
"ĩu": 267,
|
| 270 |
+
"ịu": 268,
|
| 271 |
+
"oa": 269,
|
| 272 |
+
"óa": 270,
|
| 273 |
+
"òa": 271,
|
| 274 |
+
"ỏa": 272,
|
| 275 |
+
"õa": 273,
|
| 276 |
+
"ọa": 274,
|
| 277 |
+
"oà": 275,
|
| 278 |
+
"óc": 276,
|
| 279 |
+
"ọc": 277,
|
| 280 |
+
"oe": 278,
|
| 281 |
+
"óe": 279,
|
| 282 |
+
"òe": 280,
|
| 283 |
+
"ỏe": 281,
|
| 284 |
+
"ọe": 282,
|
| 285 |
+
"oẹ": 283,
|
| 286 |
+
"oi": 284,
|
| 287 |
+
"ói": 285,
|
| 288 |
+
"òi": 286,
|
| 289 |
+
"ỏi": 287,
|
| 290 |
+
"õi": 288,
|
| 291 |
+
"ọi": 289,
|
| 292 |
+
"om": 290,
|
| 293 |
+
"óm": 291,
|
| 294 |
+
"òm": 292,
|
| 295 |
+
"ỏm": 293,
|
| 296 |
+
"õm": 294,
|
| 297 |
+
"ọm": 295,
|
| 298 |
+
"on": 296,
|
| 299 |
+
"ón": 297,
|
| 300 |
+
"òn": 298,
|
| 301 |
+
"ỏn": 299,
|
| 302 |
+
"õn": 300,
|
| 303 |
+
"ọn": 301,
|
| 304 |
+
"óp": 302,
|
| 305 |
+
"ọp": 303,
|
| 306 |
+
"ót": 304,
|
| 307 |
+
"ọt": 305,
|
| 308 |
+
"ốc": 306,
|
| 309 |
+
"ộc": 307,
|
| 310 |
+
"ôi": 308,
|
| 311 |
+
"ối": 309,
|
| 312 |
+
"ồi": 310,
|
| 313 |
+
"ổi": 311,
|
| 314 |
+
"ỗi": 312,
|
| 315 |
+
"ội": 313,
|
| 316 |
+
"ôm": 314,
|
| 317 |
+
"ốm": 315,
|
| 318 |
+
"ồm": 316,
|
| 319 |
+
"ổm": 317,
|
| 320 |
+
"ỗm": 318,
|
| 321 |
+
"ộm": 319,
|
| 322 |
+
"ôn": 320,
|
| 323 |
+
"ốn": 321,
|
| 324 |
+
"ồn": 322,
|
| 325 |
+
"ổn": 323,
|
| 326 |
+
"ỗn": 324,
|
| 327 |
+
"ộn": 325,
|
| 328 |
+
"ốp": 326,
|
| 329 |
+
"ộp": 327,
|
| 330 |
+
"ốt": 328,
|
| 331 |
+
"ột": 329,
|
| 332 |
+
"ơi": 330,
|
| 333 |
+
"ới": 331,
|
| 334 |
+
"ời": 332,
|
| 335 |
+
"ởi": 333,
|
| 336 |
+
"ỡi": 334,
|
| 337 |
+
"ợi": 335,
|
| 338 |
+
"ơm": 336,
|
| 339 |
+
"ớm": 337,
|
| 340 |
+
"ờm": 338,
|
| 341 |
+
"ởm": 339,
|
| 342 |
+
"ỡm": 340,
|
| 343 |
+
"ợm": 341,
|
| 344 |
+
"ơn": 342,
|
| 345 |
+
"ớn": 343,
|
| 346 |
+
"ờn": 344,
|
| 347 |
+
"ởn": 345,
|
| 348 |
+
"ỡn": 346,
|
| 349 |
+
"ợn": 347,
|
| 350 |
+
"ớp": 348,
|
| 351 |
+
"ợp": 349,
|
| 352 |
+
"ớt": 350,
|
| 353 |
+
"ợt": 351,
|
| 354 |
+
"ua": 352,
|
| 355 |
+
"úa": 353,
|
| 356 |
+
"ùa": 354,
|
| 357 |
+
"ủa": 355,
|
| 358 |
+
"ũa": 356,
|
| 359 |
+
"ụa": 357,
|
| 360 |
+
"úc": 358,
|
| 361 |
+
"ục": 359,
|
| 362 |
+
"uê": 360,
|
| 363 |
+
"uế": 361,
|
| 364 |
+
"uề": 362,
|
| 365 |
+
"uể": 363,
|
| 366 |
+
"uệ": 364,
|
| 367 |
+
"ui": 365,
|
| 368 |
+
"úi": 366,
|
| 369 |
+
"ùi": 367,
|
| 370 |
+
"ủi": 368,
|
| 371 |
+
"ũi": 369,
|
| 372 |
+
"ụi": 370,
|
| 373 |
+
"um": 371,
|
| 374 |
+
"úm": 372,
|
| 375 |
+
"ùm": 373,
|
| 376 |
+
"ủm": 374,
|
| 377 |
+
"ũm": 375,
|
| 378 |
+
"ụm": 376,
|
| 379 |
+
"un": 377,
|
| 380 |
+
"ún": 378,
|
| 381 |
+
"ùn": 379,
|
| 382 |
+
"ủn": 380,
|
| 383 |
+
"ũn": 381,
|
| 384 |
+
"ụn": 382,
|
| 385 |
+
"úp": 383,
|
| 386 |
+
"ụp": 384,
|
| 387 |
+
"út": 385,
|
| 388 |
+
"ụt": 386,
|
| 389 |
+
"uy": 387,
|
| 390 |
+
"úy": 388,
|
| 391 |
+
"ùy": 389,
|
| 392 |
+
"ủy": 390,
|
| 393 |
+
"ũy": 391,
|
| 394 |
+
"ụy": 392,
|
| 395 |
+
"ưa": 393,
|
| 396 |
+
"ứa": 394,
|
| 397 |
+
"ừa": 395,
|
| 398 |
+
"ửa": 396,
|
| 399 |
+
"ữa": 397,
|
| 400 |
+
"ựa": 398,
|
| 401 |
+
"ức": 399,
|
| 402 |
+
"ực": 400,
|
| 403 |
+
"ửi": 401,
|
| 404 |
+
"ừm": 402,
|
| 405 |
+
"uơ": 403,
|
| 406 |
+
"uở": 404,
|
| 407 |
+
"ứt": 405,
|
| 408 |
+
"ựt": 406,
|
| 409 |
+
"ưu": 407,
|
| 410 |
+
"ứu": 408,
|
| 411 |
+
"ừu": 409,
|
| 412 |
+
"ửu": 410,
|
| 413 |
+
"ữu": 411,
|
| 414 |
+
"ựu": 412,
|
| 415 |
+
"sh": 413,
|
| 416 |
+
"aw": 414,
|
| 417 |
+
"ee": 415,
|
| 418 |
+
"ea": 416,
|
| 419 |
+
"ei": 417,
|
| 420 |
+
"ew": 418,
|
| 421 |
+
"eu": 419,
|
| 422 |
+
"ie": 420,
|
| 423 |
+
"oo": 421,
|
| 424 |
+
"ou": 422,
|
| 425 |
+
"ow": 423,
|
| 426 |
+
"oy": 424,
|
| 427 |
+
"ue": 425,
|
| 428 |
+
"io": 426,
|
| 429 |
+
"ách": 427,
|
| 430 |
+
"ạch": 428,
|
| 431 |
+
"ang": 429,
|
| 432 |
+
"áng": 430,
|
| 433 |
+
"àng": 431,
|
| 434 |
+
"ảng": 432,
|
| 435 |
+
"ãng": 433,
|
| 436 |
+
"ạng": 434,
|
| 437 |
+
"anh": 435,
|
| 438 |
+
"ánh": 436,
|
| 439 |
+
"ành": 437,
|
| 440 |
+
"ảnh": 438,
|
| 441 |
+
"ãnh": 439,
|
| 442 |
+
"ạnh": 440,
|
| 443 |
+
"ăng": 441,
|
| 444 |
+
"ắng": 442,
|
| 445 |
+
"ằng": 443,
|
| 446 |
+
"ẳng": 444,
|
| 447 |
+
"ẵng": 445,
|
| 448 |
+
"ặng": 446,
|
| 449 |
+
"âng": 447,
|
| 450 |
+
"ấng": 448,
|
| 451 |
+
"ầng": 449,
|
| 452 |
+
"ẩng": 450,
|
| 453 |
+
"ẫng": 451,
|
| 454 |
+
"ậng": 452,
|
| 455 |
+
"eng": 453,
|
| 456 |
+
"éng": 454,
|
| 457 |
+
"èng": 455,
|
| 458 |
+
"ẻng": 456,
|
| 459 |
+
"ếch": 457,
|
| 460 |
+
"ệch": 458,
|
| 461 |
+
"ênh": 459,
|
| 462 |
+
"ếnh": 460,
|
| 463 |
+
"ềnh": 461,
|
| 464 |
+
"ểnh": 462,
|
| 465 |
+
"ễnh": 463,
|
| 466 |
+
"ệnh": 464,
|
| 467 |
+
"ích": 465,
|
| 468 |
+
"ịch": 466,
|
| 469 |
+
"iếc": 467,
|
| 470 |
+
"iệc": 468,
|
| 471 |
+
"iêm": 469,
|
| 472 |
+
"iếm": 470,
|
| 473 |
+
"iềm": 471,
|
| 474 |
+
"iểm": 472,
|
| 475 |
+
"iễm": 473,
|
| 476 |
+
"iệm": 474,
|
| 477 |
+
"iên": 475,
|
| 478 |
+
"iến": 476,
|
| 479 |
+
"iền": 477,
|
| 480 |
+
"iển": 478,
|
| 481 |
+
"iễn": 479,
|
| 482 |
+
"iện": 480,
|
| 483 |
+
"iếp": 481,
|
| 484 |
+
"iệp": 482,
|
| 485 |
+
"iết": 483,
|
| 486 |
+
"iệt": 484,
|
| 487 |
+
"iêu": 485,
|
| 488 |
+
"iếu": 486,
|
| 489 |
+
"iều": 487,
|
| 490 |
+
"iểu": 488,
|
| 491 |
+
"iễu": 489,
|
| 492 |
+
"iệu": 490,
|
| 493 |
+
"inh": 491,
|
| 494 |
+
"ính": 492,
|
| 495 |
+
"ình": 493,
|
| 496 |
+
"ỉnh": 494,
|
| 497 |
+
"ĩnh": 495,
|
| 498 |
+
"ịnh": 496,
|
| 499 |
+
"oác": 497,
|
| 500 |
+
"oạc": 498,
|
| 501 |
+
"oai": 499,
|
| 502 |
+
"oái": 500,
|
| 503 |
+
"oài": 501,
|
| 504 |
+
"oải": 502,
|
| 505 |
+
"oãi": 503,
|
| 506 |
+
"oại": 504,
|
| 507 |
+
"oàm": 505,
|
| 508 |
+
"oan": 506,
|
| 509 |
+
"oán": 507,
|
| 510 |
+
"oàn": 508,
|
| 511 |
+
"oản": 509,
|
| 512 |
+
"oãn": 510,
|
| 513 |
+
"oạn": 511,
|
| 514 |
+
"oao": 512,
|
| 515 |
+
"oáo": 513,
|
| 516 |
+
"oáp": 514,
|
| 517 |
+
"oạp": 515,
|
| 518 |
+
"oát": 516,
|
| 519 |
+
"oạt": 517,
|
| 520 |
+
"oay": 518,
|
| 521 |
+
"oáy": 519,
|
| 522 |
+
"oảy": 520,
|
| 523 |
+
"oắc": 521,
|
| 524 |
+
"oặc": 522,
|
| 525 |
+
"oăm": 523,
|
| 526 |
+
"oăn": 524,
|
| 527 |
+
"oẳn": 525,
|
| 528 |
+
"oắn": 526,
|
| 529 |
+
"oằn": 527,
|
| 530 |
+
"oắt": 528,
|
| 531 |
+
"oặt": 529,
|
| 532 |
+
"oen": 530,
|
| 533 |
+
"oẻn": 531,
|
| 534 |
+
"oeo": 532,
|
| 535 |
+
"oéo": 533,
|
| 536 |
+
"oèo": 534,
|
| 537 |
+
"oẻo": 535,
|
| 538 |
+
"oét": 536,
|
| 539 |
+
"oẹt": 537,
|
| 540 |
+
"ong": 538,
|
| 541 |
+
"óng": 539,
|
| 542 |
+
"òng": 540,
|
| 543 |
+
"ỏng": 541,
|
| 544 |
+
"õng": 542,
|
| 545 |
+
"ọng": 543,
|
| 546 |
+
"oóc": 544,
|
| 547 |
+
"oọc": 545,
|
| 548 |
+
"ông": 546,
|
| 549 |
+
"ống": 547,
|
| 550 |
+
"ồng": 548,
|
| 551 |
+
"ổng": 549,
|
| 552 |
+
"ỗng": 550,
|
| 553 |
+
"ộng": 551,
|
| 554 |
+
"uân": 552,
|
| 555 |
+
"uấn": 553,
|
| 556 |
+
"uần": 554,
|
| 557 |
+
"uẩn": 555,
|
| 558 |
+
"uẫn": 556,
|
| 559 |
+
"uận": 557,
|
| 560 |
+
"uất": 558,
|
| 561 |
+
"uật": 559,
|
| 562 |
+
"uây": 560,
|
| 563 |
+
"uấy": 561,
|
| 564 |
+
"uầy": 562,
|
| 565 |
+
"ung": 563,
|
| 566 |
+
"úng": 564,
|
| 567 |
+
"ùng": 565,
|
| 568 |
+
"ủng": 566,
|
| 569 |
+
"ũng": 567,
|
| 570 |
+
"ụng": 568,
|
| 571 |
+
"uốc": 569,
|
| 572 |
+
"uộc": 570,
|
| 573 |
+
"uôi": 571,
|
| 574 |
+
"uối": 572,
|
| 575 |
+
"uồi": 573,
|
| 576 |
+
"uổi": 574,
|
| 577 |
+
"uỗi": 575,
|
| 578 |
+
"uội": 576,
|
| 579 |
+
"uôm": 577,
|
| 580 |
+
"uốm": 578,
|
| 581 |
+
"uồm": 579,
|
| 582 |
+
"uỗm": 580,
|
| 583 |
+
"uộm": 581,
|
| 584 |
+
"uôn": 582,
|
| 585 |
+
"uốn": 583,
|
| 586 |
+
"uồn": 584,
|
| 587 |
+
"uỗn": 585,
|
| 588 |
+
"uộn": 586,
|
| 589 |
+
"uốt": 587,
|
| 590 |
+
"uột": 588,
|
| 591 |
+
"uýt": 589,
|
| 592 |
+
"uỵt": 590,
|
| 593 |
+
"uya": 591,
|
| 594 |
+
"uỷu": 592,
|
| 595 |
+
"ưng": 593,
|
| 596 |
+
"ứng": 594,
|
| 597 |
+
"ừng": 595,
|
| 598 |
+
"ửng": 596,
|
| 599 |
+
"ững": 597,
|
| 600 |
+
"ựng": 598,
|
| 601 |
+
"ước": 599,
|
| 602 |
+
"ược": 600,
|
| 603 |
+
"ươi": 601,
|
| 604 |
+
"ưới": 602,
|
| 605 |
+
"ười": 603,
|
| 606 |
+
"ưởi": 604,
|
| 607 |
+
"ưỡi": 605,
|
| 608 |
+
"ượi": 606,
|
| 609 |
+
"ươm": 607,
|
| 610 |
+
"ướm": 608,
|
| 611 |
+
"ườm": 609,
|
| 612 |
+
"ượm": 610,
|
| 613 |
+
"ươn": 611,
|
| 614 |
+
"ướn": 612,
|
| 615 |
+
"ườn": 613,
|
| 616 |
+
"ưỡn": 614,
|
| 617 |
+
"ượn": 615,
|
| 618 |
+
"ướp": 616,
|
| 619 |
+
"ượp": 617,
|
| 620 |
+
"ướt": 618,
|
| 621 |
+
"ượt": 619,
|
| 622 |
+
"ươu": 620,
|
| 623 |
+
"ướu": 621,
|
| 624 |
+
"ượu": 622,
|
| 625 |
+
"yêm": 623,
|
| 626 |
+
"yếm": 624,
|
| 627 |
+
"yểm": 625,
|
| 628 |
+
"yên": 626,
|
| 629 |
+
"yến": 627,
|
| 630 |
+
"yêu": 628,
|
| 631 |
+
"yếu": 629,
|
| 632 |
+
"yểu": 630,
|
| 633 |
+
"yết": 631,
|
| 634 |
+
"iêng": 632,
|
| 635 |
+
"iếng": 633,
|
| 636 |
+
"iềng": 634,
|
| 637 |
+
"iểng": 635,
|
| 638 |
+
"iễng": 636,
|
| 639 |
+
"iệng": 637,
|
| 640 |
+
"oách": 638,
|
| 641 |
+
"oạch": 639,
|
| 642 |
+
"oang": 640,
|
| 643 |
+
"oáng": 641,
|
| 644 |
+
"oàng": 642,
|
| 645 |
+
"oảng": 643,
|
| 646 |
+
"oãng": 644,
|
| 647 |
+
"oạng": 645,
|
| 648 |
+
"oanh": 646,
|
| 649 |
+
"oánh": 647,
|
| 650 |
+
"oành": 648,
|
| 651 |
+
"oạnh": 649,
|
| 652 |
+
"oảnh": 650,
|
| 653 |
+
"oăng": 651,
|
| 654 |
+
"oắng": 652,
|
| 655 |
+
"oằng": 653,
|
| 656 |
+
"oẳng": 654,
|
| 657 |
+
"oong": 655,
|
| 658 |
+
"uếch": 656,
|
| 659 |
+
"uênh": 657,
|
| 660 |
+
"uông": 658,
|
| 661 |
+
"uống": 659,
|
| 662 |
+
"uồng": 660,
|
| 663 |
+
"uổng": 661,
|
| 664 |
+
"uỗng": 662,
|
| 665 |
+
"uộng": 663,
|
| 666 |
+
"uých": 664,
|
| 667 |
+
"uỵch": 665,
|
| 668 |
+
"uyên": 666,
|
| 669 |
+
"uyến": 667,
|
| 670 |
+
"uyền": 668,
|
| 671 |
+
"uyển": 669,
|
| 672 |
+
"uyễn": 670,
|
| 673 |
+
"uyện": 671,
|
| 674 |
+
"uyết": 672,
|
| 675 |
+
"uyệt": 673,
|
| 676 |
+
"uynh": 674,
|
| 677 |
+
"uỳnh": 675,
|
| 678 |
+
"uýnh": 676,
|
| 679 |
+
"uỷnh": 677,
|
| 680 |
+
"ương": 678,
|
| 681 |
+
"ướng": 679,
|
| 682 |
+
"ường": 680,
|
| 683 |
+
"ưởng": 681,
|
| 684 |
+
"ưỡng": 682,
|
| 685 |
+
"ượng": 683,
|
| 686 |
+
"op": 684,
|
| 687 |
+
"ot": 685,
|
| 688 |
+
"gi": 686,
|
| 689 |
+
"ap": 687,
|
| 690 |
+
"at": 688,
|
| 691 |
+
"ac": 689,
|
| 692 |
+
"it": 690,
|
| 693 |
+
"ip": 691,
|
| 694 |
+
"ic": 692,
|
| 695 |
+
"ep": 693,
|
| 696 |
+
"et": 694,
|
| 697 |
+
"ec": 695,
|
| 698 |
+
"1": 696,
|
| 699 |
+
"2": 697,
|
| 700 |
+
"3": 698,
|
| 701 |
+
"4": 699,
|
| 702 |
+
"5": 700,
|
| 703 |
+
"6": 701,
|
| 704 |
+
"7": 702,
|
| 705 |
+
"8": 703,
|
| 706 |
+
"9": 704,
|
| 707 |
+
"0": 705
|
| 708 |
+
}
|