Training in progress, step 2000
Browse files- added_tokens.json +79 -79
- config.json +92 -92
- model.safetensors +1 -1
- preprocessor_config.json +19 -0
- special_tokens_map.json +37 -13
- tokenizer_config.json +680 -680
- training_args.bin +2 -2
added_tokens.json
CHANGED
@@ -1,79 +1,79 @@
|
|
1 |
-
{
|
2 |
-
" ": 155,
|
3 |
-
"0": 154,
|
4 |
-
"1": 145,
|
5 |
-
"2": 146,
|
6 |
-
"3": 147,
|
7 |
-
"4": 148,
|
8 |
-
"5": 149,
|
9 |
-
"6": 150,
|
10 |
-
"7": 151,
|
11 |
-
"8": 152,
|
12 |
-
"9": 153,
|
13 |
-
"<ctc_blank>": 80,
|
14 |
-
"<mask>": 79,
|
15 |
-
"à": 82,
|
16 |
-
"á": 81,
|
17 |
-
"â": 86,
|
18 |
-
"ã": 85,
|
19 |
-
"è": 97,
|
20 |
-
"ì": 119,
|
21 |
-
"í": 118,
|
22 |
-
"ò": 102,
|
23 |
-
"ó": 101,
|
24 |
-
"ô": 111,
|
25 |
-
"õ": 104,
|
26 |
-
"ù": 140,
|
27 |
-
"ú": 139,
|
28 |
-
"ý": 123,
|
29 |
-
"ă": 92,
|
30 |
-
"đ": 144,
|
31 |
-
"ĩ": 121,
|
32 |
-
"ũ": 142,
|
33 |
-
"ơ": 117,
|
34 |
-
"ư": 138,
|
35 |
-
"ạ": 83,
|
36 |
-
"ả": 84,
|
37 |
-
"ấ": 88,
|
38 |
-
"ầ": 89,
|
39 |
-
"ẩ": 87,
|
40 |
-
"ẫ": 91,
|
41 |
-
"ậ": 90,
|
42 |
-
"ắ": 93,
|
43 |
-
"ằ": 94,
|
44 |
-
"ẳ": 96,
|
45 |
-
"ặ": 95,
|
46 |
-
"ẹ": 100,
|
47 |
-
"ẻ": 98,
|
48 |
-
"ẽ": 99,
|
49 |
-
"ế": 128,
|
50 |
-
"ề": 129,
|
51 |
-
"ể": 130,
|
52 |
-
"ễ": 131,
|
53 |
-
"ệ": 132,
|
54 |
-
"ỉ": 122,
|
55 |
-
"ị": 120,
|
56 |
-
"ọ": 105,
|
57 |
-
"ỏ": 103,
|
58 |
-
"ố": 106,
|
59 |
-
"ồ": 107,
|
60 |
-
"ổ": 109,
|
61 |
-
"ỗ": 108,
|
62 |
-
"ộ": 110,
|
63 |
-
"ớ": 112,
|
64 |
-
"ờ": 113,
|
65 |
-
"ở": 114,
|
66 |
-
"ỡ": 115,
|
67 |
-
"ợ": 116,
|
68 |
-
"ụ": 143,
|
69 |
-
"ủ": 141,
|
70 |
-
"ứ": 133,
|
71 |
-
"ừ": 134,
|
72 |
-
"ử": 135,
|
73 |
-
"ữ": 136,
|
74 |
-
"ự": 137,
|
75 |
-
"ỳ": 124,
|
76 |
-
"ỵ": 127,
|
77 |
-
"ỷ": 125,
|
78 |
-
"ỹ": 126
|
79 |
-
}
|
|
|
1 |
+
{
|
2 |
+
" ": 155,
|
3 |
+
"0": 154,
|
4 |
+
"1": 145,
|
5 |
+
"2": 146,
|
6 |
+
"3": 147,
|
7 |
+
"4": 148,
|
8 |
+
"5": 149,
|
9 |
+
"6": 150,
|
10 |
+
"7": 151,
|
11 |
+
"8": 152,
|
12 |
+
"9": 153,
|
13 |
+
"<ctc_blank>": 80,
|
14 |
+
"<mask>": 79,
|
15 |
+
"à": 82,
|
16 |
+
"á": 81,
|
17 |
+
"â": 86,
|
18 |
+
"ã": 85,
|
19 |
+
"è": 97,
|
20 |
+
"ì": 119,
|
21 |
+
"í": 118,
|
22 |
+
"ò": 102,
|
23 |
+
"ó": 101,
|
24 |
+
"ô": 111,
|
25 |
+
"õ": 104,
|
26 |
+
"ù": 140,
|
27 |
+
"ú": 139,
|
28 |
+
"ý": 123,
|
29 |
+
"ă": 92,
|
30 |
+
"đ": 144,
|
31 |
+
"ĩ": 121,
|
32 |
+
"ũ": 142,
|
33 |
+
"ơ": 117,
|
34 |
+
"ư": 138,
|
35 |
+
"ạ": 83,
|
36 |
+
"ả": 84,
|
37 |
+
"ấ": 88,
|
38 |
+
"ầ": 89,
|
39 |
+
"ẩ": 87,
|
40 |
+
"ẫ": 91,
|
41 |
+
"ậ": 90,
|
42 |
+
"ắ": 93,
|
43 |
+
"ằ": 94,
|
44 |
+
"ẳ": 96,
|
45 |
+
"ặ": 95,
|
46 |
+
"ẹ": 100,
|
47 |
+
"ẻ": 98,
|
48 |
+
"ẽ": 99,
|
49 |
+
"ế": 128,
|
50 |
+
"ề": 129,
|
51 |
+
"ể": 130,
|
52 |
+
"ễ": 131,
|
53 |
+
"ệ": 132,
|
54 |
+
"ỉ": 122,
|
55 |
+
"ị": 120,
|
56 |
+
"ọ": 105,
|
57 |
+
"ỏ": 103,
|
58 |
+
"ố": 106,
|
59 |
+
"ồ": 107,
|
60 |
+
"ổ": 109,
|
61 |
+
"ỗ": 108,
|
62 |
+
"ộ": 110,
|
63 |
+
"ớ": 112,
|
64 |
+
"ờ": 113,
|
65 |
+
"ở": 114,
|
66 |
+
"ỡ": 115,
|
67 |
+
"ợ": 116,
|
68 |
+
"ụ": 143,
|
69 |
+
"ủ": 141,
|
70 |
+
"ứ": 133,
|
71 |
+
"ừ": 134,
|
72 |
+
"ử": 135,
|
73 |
+
"ữ": 136,
|
74 |
+
"ự": 137,
|
75 |
+
"ỳ": 124,
|
76 |
+
"ỵ": 127,
|
77 |
+
"ỷ": 125,
|
78 |
+
"ỹ": 126
|
79 |
+
}
|
config.json
CHANGED
@@ -1,92 +1,92 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "linl03/voice_vi_female",
|
3 |
-
"activation_dropout": 0.1,
|
4 |
-
"apply_spec_augment": true,
|
5 |
-
"architectures": [
|
6 |
-
"SpeechT5ForTextToSpeech"
|
7 |
-
],
|
8 |
-
"attention_dropout": 0.1,
|
9 |
-
"bos_token_id": 0,
|
10 |
-
"conv_bias": false,
|
11 |
-
"conv_dim": [
|
12 |
-
512,
|
13 |
-
512,
|
14 |
-
512,
|
15 |
-
512,
|
16 |
-
512,
|
17 |
-
512,
|
18 |
-
512
|
19 |
-
],
|
20 |
-
"conv_kernel": [
|
21 |
-
10,
|
22 |
-
3,
|
23 |
-
3,
|
24 |
-
3,
|
25 |
-
3,
|
26 |
-
2,
|
27 |
-
2
|
28 |
-
],
|
29 |
-
"conv_stride": [
|
30 |
-
5,
|
31 |
-
2,
|
32 |
-
2,
|
33 |
-
2,
|
34 |
-
2,
|
35 |
-
2,
|
36 |
-
2
|
37 |
-
],
|
38 |
-
"decoder_attention_heads": 12,
|
39 |
-
"decoder_ffn_dim": 3072,
|
40 |
-
"decoder_layerdrop": 0.1,
|
41 |
-
"decoder_layers": 6,
|
42 |
-
"decoder_start_token_id": 2,
|
43 |
-
"encoder_attention_heads": 12,
|
44 |
-
"encoder_ffn_dim": 3072,
|
45 |
-
"encoder_layerdrop": 0.1,
|
46 |
-
"encoder_layers": 12,
|
47 |
-
"encoder_max_relative_position": 160,
|
48 |
-
"eos_token_id": 2,
|
49 |
-
"feat_extract_activation": "gelu",
|
50 |
-
"feat_extract_norm": "group",
|
51 |
-
"feat_proj_dropout": 0.0,
|
52 |
-
"guided_attention_loss_num_heads": 2,
|
53 |
-
"guided_attention_loss_scale": 10.0,
|
54 |
-
"guided_attention_loss_sigma": 0.4,
|
55 |
-
"hidden_act": "gelu",
|
56 |
-
"hidden_dropout": 0.1,
|
57 |
-
"hidden_size": 768,
|
58 |
-
"initializer_range": 0.02,
|
59 |
-
"is_encoder_decoder": true,
|
60 |
-
"layer_norm_eps": 1e-05,
|
61 |
-
"mask_feature_length": 10,
|
62 |
-
"mask_feature_min_masks": 0,
|
63 |
-
"mask_feature_prob": 0.0,
|
64 |
-
"mask_time_length": 10,
|
65 |
-
"mask_time_min_masks": 2,
|
66 |
-
"mask_time_prob": 0.05,
|
67 |
-
"max_length": null,
|
68 |
-
"max_speech_positions": 1876,
|
69 |
-
"max_text_positions": 600,
|
70 |
-
"model_type": "speecht5",
|
71 |
-
"num_conv_pos_embedding_groups": 16,
|
72 |
-
"num_conv_pos_embeddings": 128,
|
73 |
-
"num_feat_extract_layers": 7,
|
74 |
-
"num_mel_bins": 80,
|
75 |
-
"pad_token_id": 1,
|
76 |
-
"positional_dropout": 0.1,
|
77 |
-
"reduction_factor": 2,
|
78 |
-
"scale_embedding": false,
|
79 |
-
"speaker_embedding_dim": 512,
|
80 |
-
"speech_decoder_postnet_dropout": 0.5,
|
81 |
-
"speech_decoder_postnet_kernel": 5,
|
82 |
-
"speech_decoder_postnet_layers": 5,
|
83 |
-
"speech_decoder_postnet_units": 256,
|
84 |
-
"speech_decoder_prenet_dropout": 0.5,
|
85 |
-
"speech_decoder_prenet_layers": 2,
|
86 |
-
"speech_decoder_prenet_units": 256,
|
87 |
-
"torch_dtype": "float32",
|
88 |
-
"transformers_version": "4.
|
89 |
-
"use_cache": false,
|
90 |
-
"use_guided_attention_loss": true,
|
91 |
-
"vocab_size": 156
|
92 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "linl03/voice_vi_female",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"apply_spec_augment": true,
|
5 |
+
"architectures": [
|
6 |
+
"SpeechT5ForTextToSpeech"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"conv_bias": false,
|
11 |
+
"conv_dim": [
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512
|
19 |
+
],
|
20 |
+
"conv_kernel": [
|
21 |
+
10,
|
22 |
+
3,
|
23 |
+
3,
|
24 |
+
3,
|
25 |
+
3,
|
26 |
+
2,
|
27 |
+
2
|
28 |
+
],
|
29 |
+
"conv_stride": [
|
30 |
+
5,
|
31 |
+
2,
|
32 |
+
2,
|
33 |
+
2,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2
|
37 |
+
],
|
38 |
+
"decoder_attention_heads": 12,
|
39 |
+
"decoder_ffn_dim": 3072,
|
40 |
+
"decoder_layerdrop": 0.1,
|
41 |
+
"decoder_layers": 6,
|
42 |
+
"decoder_start_token_id": 2,
|
43 |
+
"encoder_attention_heads": 12,
|
44 |
+
"encoder_ffn_dim": 3072,
|
45 |
+
"encoder_layerdrop": 0.1,
|
46 |
+
"encoder_layers": 12,
|
47 |
+
"encoder_max_relative_position": 160,
|
48 |
+
"eos_token_id": 2,
|
49 |
+
"feat_extract_activation": "gelu",
|
50 |
+
"feat_extract_norm": "group",
|
51 |
+
"feat_proj_dropout": 0.0,
|
52 |
+
"guided_attention_loss_num_heads": 2,
|
53 |
+
"guided_attention_loss_scale": 10.0,
|
54 |
+
"guided_attention_loss_sigma": 0.4,
|
55 |
+
"hidden_act": "gelu",
|
56 |
+
"hidden_dropout": 0.1,
|
57 |
+
"hidden_size": 768,
|
58 |
+
"initializer_range": 0.02,
|
59 |
+
"is_encoder_decoder": true,
|
60 |
+
"layer_norm_eps": 1e-05,
|
61 |
+
"mask_feature_length": 10,
|
62 |
+
"mask_feature_min_masks": 0,
|
63 |
+
"mask_feature_prob": 0.0,
|
64 |
+
"mask_time_length": 10,
|
65 |
+
"mask_time_min_masks": 2,
|
66 |
+
"mask_time_prob": 0.05,
|
67 |
+
"max_length": null,
|
68 |
+
"max_speech_positions": 1876,
|
69 |
+
"max_text_positions": 600,
|
70 |
+
"model_type": "speecht5",
|
71 |
+
"num_conv_pos_embedding_groups": 16,
|
72 |
+
"num_conv_pos_embeddings": 128,
|
73 |
+
"num_feat_extract_layers": 7,
|
74 |
+
"num_mel_bins": 80,
|
75 |
+
"pad_token_id": 1,
|
76 |
+
"positional_dropout": 0.1,
|
77 |
+
"reduction_factor": 2,
|
78 |
+
"scale_embedding": false,
|
79 |
+
"speaker_embedding_dim": 512,
|
80 |
+
"speech_decoder_postnet_dropout": 0.5,
|
81 |
+
"speech_decoder_postnet_kernel": 5,
|
82 |
+
"speech_decoder_postnet_layers": 5,
|
83 |
+
"speech_decoder_postnet_units": 256,
|
84 |
+
"speech_decoder_prenet_dropout": 0.5,
|
85 |
+
"speech_decoder_prenet_layers": 2,
|
86 |
+
"speech_decoder_prenet_units": 256,
|
87 |
+
"torch_dtype": "float32",
|
88 |
+
"transformers_version": "4.50.0.dev0",
|
89 |
+
"use_cache": false,
|
90 |
+
"use_guided_attention_loss": true,
|
91 |
+
"vocab_size": 156
|
92 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 578019720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a0f9d5fdc4a8b6c82863e2332ac31352b0aeb7bd1d17a94505251bfc8b438f2
|
3 |
size 578019720
|
preprocessor_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": false,
|
3 |
+
"feature_extractor_type": "SpeechT5FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"fmax": 7600,
|
6 |
+
"fmin": 80,
|
7 |
+
"frame_signal_scale": 1.0,
|
8 |
+
"hop_length": 16,
|
9 |
+
"mel_floor": 1e-10,
|
10 |
+
"num_mel_bins": 80,
|
11 |
+
"padding_side": "right",
|
12 |
+
"padding_value": 0.0,
|
13 |
+
"processor_class": "SpeechT5Processor",
|
14 |
+
"reduction_factor": 2,
|
15 |
+
"return_attention_mask": true,
|
16 |
+
"sampling_rate": 16000,
|
17 |
+
"win_function": "hann_window",
|
18 |
+
"win_length": 64
|
19 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1,13 +1,37 @@
|
|
1 |
-
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"mask_token": {
|
17 |
+
"content": "<mask>",
|
18 |
+
"lstrip": true,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"pad_token": {
|
24 |
+
"content": "<pad>",
|
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_config.json
CHANGED
@@ -1,680 +1,680 @@
|
|
1 |
-
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"0": {
|
4 |
-
"content": "<s>",
|
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": "</s>",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"3": {
|
28 |
-
"content": "<unk>",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"73": {
|
36 |
-
"content": "é",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": true,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": false
|
42 |
-
},
|
43 |
-
"76": {
|
44 |
-
"content": "ê",
|
45 |
-
"lstrip": false,
|
46 |
-
"normalized": true,
|
47 |
-
"rstrip": false,
|
48 |
-
"single_word": false,
|
49 |
-
"special": false
|
50 |
-
},
|
51 |
-
"79": {
|
52 |
-
"content": "<mask>",
|
53 |
-
"lstrip": true,
|
54 |
-
"normalized": true,
|
55 |
-
"rstrip": false,
|
56 |
-
"single_word": false,
|
57 |
-
"special": true
|
58 |
-
},
|
59 |
-
"80": {
|
60 |
-
"content": "<ctc_blank>",
|
61 |
-
"lstrip": false,
|
62 |
-
"normalized": true,
|
63 |
-
"rstrip": false,
|
64 |
-
"single_word": false,
|
65 |
-
"special": false
|
66 |
-
},
|
67 |
-
"81": {
|
68 |
-
"content": "á",
|
69 |
-
"lstrip": false,
|
70 |
-
"normalized": true,
|
71 |
-
"rstrip": false,
|
72 |
-
"single_word": false,
|
73 |
-
"special": false
|
74 |
-
},
|
75 |
-
"82": {
|
76 |
-
"content": "à",
|
77 |
-
"lstrip": false,
|
78 |
-
"normalized": true,
|
79 |
-
"rstrip": false,
|
80 |
-
"single_word": false,
|
81 |
-
"special": false
|
82 |
-
},
|
83 |
-
"83": {
|
84 |
-
"content": "ạ",
|
85 |
-
"lstrip": false,
|
86 |
-
"normalized": true,
|
87 |
-
"rstrip": false,
|
88 |
-
"single_word": false,
|
89 |
-
"special": false
|
90 |
-
},
|
91 |
-
"84": {
|
92 |
-
"content": "ả",
|
93 |
-
"lstrip": false,
|
94 |
-
"normalized": true,
|
95 |
-
"rstrip": false,
|
96 |
-
"single_word": false,
|
97 |
-
"special": false
|
98 |
-
},
|
99 |
-
"85": {
|
100 |
-
"content": "ã",
|
101 |
-
"lstrip": false,
|
102 |
-
"normalized": true,
|
103 |
-
"rstrip": false,
|
104 |
-
"single_word": false,
|
105 |
-
"special": false
|
106 |
-
},
|
107 |
-
"86": {
|
108 |
-
"content": "â",
|
109 |
-
"lstrip": false,
|
110 |
-
"normalized": true,
|
111 |
-
"rstrip": false,
|
112 |
-
"single_word": false,
|
113 |
-
"special": false
|
114 |
-
},
|
115 |
-
"87": {
|
116 |
-
"content": "ẩ",
|
117 |
-
"lstrip": false,
|
118 |
-
"normalized": true,
|
119 |
-
"rstrip": false,
|
120 |
-
"single_word": false,
|
121 |
-
"special": false
|
122 |
-
},
|
123 |
-
"88": {
|
124 |
-
"content": "ấ",
|
125 |
-
"lstrip": false,
|
126 |
-
"normalized": true,
|
127 |
-
"rstrip": false,
|
128 |
-
"single_word": false,
|
129 |
-
"special": false
|
130 |
-
},
|
131 |
-
"89": {
|
132 |
-
"content": "ầ",
|
133 |
-
"lstrip": false,
|
134 |
-
"normalized": true,
|
135 |
-
"rstrip": false,
|
136 |
-
"single_word": false,
|
137 |
-
"special": false
|
138 |
-
},
|
139 |
-
"90": {
|
140 |
-
"content": "ậ",
|
141 |
-
"lstrip": false,
|
142 |
-
"normalized": true,
|
143 |
-
"rstrip": false,
|
144 |
-
"single_word": false,
|
145 |
-
"special": false
|
146 |
-
},
|
147 |
-
"91": {
|
148 |
-
"content": "ẫ",
|
149 |
-
"lstrip": false,
|
150 |
-
"normalized": true,
|
151 |
-
"rstrip": false,
|
152 |
-
"single_word": false,
|
153 |
-
"special": false
|
154 |
-
},
|
155 |
-
"92": {
|
156 |
-
"content": "ă",
|
157 |
-
"lstrip": false,
|
158 |
-
"normalized": true,
|
159 |
-
"rstrip": false,
|
160 |
-
"single_word": false,
|
161 |
-
"special": false
|
162 |
-
},
|
163 |
-
"93": {
|
164 |
-
"content": "ắ",
|
165 |
-
"lstrip": false,
|
166 |
-
"normalized": true,
|
167 |
-
"rstrip": false,
|
168 |
-
"single_word": false,
|
169 |
-
"special": false
|
170 |
-
},
|
171 |
-
"94": {
|
172 |
-
"content": "ằ",
|
173 |
-
"lstrip": false,
|
174 |
-
"normalized": true,
|
175 |
-
"rstrip": false,
|
176 |
-
"single_word": false,
|
177 |
-
"special": false
|
178 |
-
},
|
179 |
-
"95": {
|
180 |
-
"content": "ặ",
|
181 |
-
"lstrip": false,
|
182 |
-
"normalized": true,
|
183 |
-
"rstrip": false,
|
184 |
-
"single_word": false,
|
185 |
-
"special": false
|
186 |
-
},
|
187 |
-
"96": {
|
188 |
-
"content": "ẳ",
|
189 |
-
"lstrip": false,
|
190 |
-
"normalized": true,
|
191 |
-
"rstrip": false,
|
192 |
-
"single_word": false,
|
193 |
-
"special": false
|
194 |
-
},
|
195 |
-
"97": {
|
196 |
-
"content": "è",
|
197 |
-
"lstrip": false,
|
198 |
-
"normalized": true,
|
199 |
-
"rstrip": false,
|
200 |
-
"single_word": false,
|
201 |
-
"special": false
|
202 |
-
},
|
203 |
-
"98": {
|
204 |
-
"content": "ẻ",
|
205 |
-
"lstrip": false,
|
206 |
-
"normalized": true,
|
207 |
-
"rstrip": false,
|
208 |
-
"single_word": false,
|
209 |
-
"special": false
|
210 |
-
},
|
211 |
-
"99": {
|
212 |
-
"content": "ẽ",
|
213 |
-
"lstrip": false,
|
214 |
-
"normalized": true,
|
215 |
-
"rstrip": false,
|
216 |
-
"single_word": false,
|
217 |
-
"special": false
|
218 |
-
},
|
219 |
-
"100": {
|
220 |
-
"content": "ẹ",
|
221 |
-
"lstrip": false,
|
222 |
-
"normalized": true,
|
223 |
-
"rstrip": false,
|
224 |
-
"single_word": false,
|
225 |
-
"special": false
|
226 |
-
},
|
227 |
-
"101": {
|
228 |
-
"content": "ó",
|
229 |
-
"lstrip": false,
|
230 |
-
"normalized": true,
|
231 |
-
"rstrip": false,
|
232 |
-
"single_word": false,
|
233 |
-
"special": false
|
234 |
-
},
|
235 |
-
"102": {
|
236 |
-
"content": "ò",
|
237 |
-
"lstrip": false,
|
238 |
-
"normalized": true,
|
239 |
-
"rstrip": false,
|
240 |
-
"single_word": false,
|
241 |
-
"special": false
|
242 |
-
},
|
243 |
-
"103": {
|
244 |
-
"content": "ỏ",
|
245 |
-
"lstrip": false,
|
246 |
-
"normalized": true,
|
247 |
-
"rstrip": false,
|
248 |
-
"single_word": false,
|
249 |
-
"special": false
|
250 |
-
},
|
251 |
-
"104": {
|
252 |
-
"content": "õ",
|
253 |
-
"lstrip": false,
|
254 |
-
"normalized": true,
|
255 |
-
"rstrip": false,
|
256 |
-
"single_word": false,
|
257 |
-
"special": false
|
258 |
-
},
|
259 |
-
"105": {
|
260 |
-
"content": "ọ",
|
261 |
-
"lstrip": false,
|
262 |
-
"normalized": true,
|
263 |
-
"rstrip": false,
|
264 |
-
"single_word": false,
|
265 |
-
"special": false
|
266 |
-
},
|
267 |
-
"106": {
|
268 |
-
"content": "ố",
|
269 |
-
"lstrip": false,
|
270 |
-
"normalized": true,
|
271 |
-
"rstrip": false,
|
272 |
-
"single_word": false,
|
273 |
-
"special": false
|
274 |
-
},
|
275 |
-
"107": {
|
276 |
-
"content": "ồ",
|
277 |
-
"lstrip": false,
|
278 |
-
"normalized": true,
|
279 |
-
"rstrip": false,
|
280 |
-
"single_word": false,
|
281 |
-
"special": false
|
282 |
-
},
|
283 |
-
"108": {
|
284 |
-
"content": "ỗ",
|
285 |
-
"lstrip": false,
|
286 |
-
"normalized": true,
|
287 |
-
"rstrip": false,
|
288 |
-
"single_word": false,
|
289 |
-
"special": false
|
290 |
-
},
|
291 |
-
"109": {
|
292 |
-
"content": "ổ",
|
293 |
-
"lstrip": false,
|
294 |
-
"normalized": true,
|
295 |
-
"rstrip": false,
|
296 |
-
"single_word": false,
|
297 |
-
"special": false
|
298 |
-
},
|
299 |
-
"110": {
|
300 |
-
"content": "ộ",
|
301 |
-
"lstrip": false,
|
302 |
-
"normalized": true,
|
303 |
-
"rstrip": false,
|
304 |
-
"single_word": false,
|
305 |
-
"special": false
|
306 |
-
},
|
307 |
-
"111": {
|
308 |
-
"content": "ô",
|
309 |
-
"lstrip": false,
|
310 |
-
"normalized": true,
|
311 |
-
"rstrip": false,
|
312 |
-
"single_word": false,
|
313 |
-
"special": false
|
314 |
-
},
|
315 |
-
"112": {
|
316 |
-
"content": "ớ",
|
317 |
-
"lstrip": false,
|
318 |
-
"normalized": true,
|
319 |
-
"rstrip": false,
|
320 |
-
"single_word": false,
|
321 |
-
"special": false
|
322 |
-
},
|
323 |
-
"113": {
|
324 |
-
"content": "ờ",
|
325 |
-
"lstrip": false,
|
326 |
-
"normalized": true,
|
327 |
-
"rstrip": false,
|
328 |
-
"single_word": false,
|
329 |
-
"special": false
|
330 |
-
},
|
331 |
-
"114": {
|
332 |
-
"content": "ở",
|
333 |
-
"lstrip": false,
|
334 |
-
"normalized": true,
|
335 |
-
"rstrip": false,
|
336 |
-
"single_word": false,
|
337 |
-
"special": false
|
338 |
-
},
|
339 |
-
"115": {
|
340 |
-
"content": "ỡ",
|
341 |
-
"lstrip": false,
|
342 |
-
"normalized": true,
|
343 |
-
"rstrip": false,
|
344 |
-
"single_word": false,
|
345 |
-
"special": false
|
346 |
-
},
|
347 |
-
"116": {
|
348 |
-
"content": "ợ",
|
349 |
-
"lstrip": false,
|
350 |
-
"normalized": true,
|
351 |
-
"rstrip": false,
|
352 |
-
"single_word": false,
|
353 |
-
"special": false
|
354 |
-
},
|
355 |
-
"117": {
|
356 |
-
"content": "ơ",
|
357 |
-
"lstrip": false,
|
358 |
-
"normalized": true,
|
359 |
-
"rstrip": false,
|
360 |
-
"single_word": false,
|
361 |
-
"special": false
|
362 |
-
},
|
363 |
-
"118": {
|
364 |
-
"content": "í",
|
365 |
-
"lstrip": false,
|
366 |
-
"normalized": true,
|
367 |
-
"rstrip": false,
|
368 |
-
"single_word": false,
|
369 |
-
"special": false
|
370 |
-
},
|
371 |
-
"119": {
|
372 |
-
"content": "ì",
|
373 |
-
"lstrip": false,
|
374 |
-
"normalized": true,
|
375 |
-
"rstrip": false,
|
376 |
-
"single_word": false,
|
377 |
-
"special": false
|
378 |
-
},
|
379 |
-
"120": {
|
380 |
-
"content": "ị",
|
381 |
-
"lstrip": false,
|
382 |
-
"normalized": true,
|
383 |
-
"rstrip": false,
|
384 |
-
"single_word": false,
|
385 |
-
"special": false
|
386 |
-
},
|
387 |
-
"121": {
|
388 |
-
"content": "ĩ",
|
389 |
-
"lstrip": false,
|
390 |
-
"normalized": true,
|
391 |
-
"rstrip": false,
|
392 |
-
"single_word": false,
|
393 |
-
"special": false
|
394 |
-
},
|
395 |
-
"122": {
|
396 |
-
"content": "ỉ",
|
397 |
-
"lstrip": false,
|
398 |
-
"normalized": true,
|
399 |
-
"rstrip": false,
|
400 |
-
"single_word": false,
|
401 |
-
"special": false
|
402 |
-
},
|
403 |
-
"123": {
|
404 |
-
"content": "ý",
|
405 |
-
"lstrip": false,
|
406 |
-
"normalized": true,
|
407 |
-
"rstrip": false,
|
408 |
-
"single_word": false,
|
409 |
-
"special": false
|
410 |
-
},
|
411 |
-
"124": {
|
412 |
-
"content": "ỳ",
|
413 |
-
"lstrip": false,
|
414 |
-
"normalized": true,
|
415 |
-
"rstrip": false,
|
416 |
-
"single_word": false,
|
417 |
-
"special": false
|
418 |
-
},
|
419 |
-
"125": {
|
420 |
-
"content": "ỷ",
|
421 |
-
"lstrip": false,
|
422 |
-
"normalized": true,
|
423 |
-
"rstrip": false,
|
424 |
-
"single_word": false,
|
425 |
-
"special": false
|
426 |
-
},
|
427 |
-
"126": {
|
428 |
-
"content": "ỹ",
|
429 |
-
"lstrip": false,
|
430 |
-
"normalized": true,
|
431 |
-
"rstrip": false,
|
432 |
-
"single_word": false,
|
433 |
-
"special": false
|
434 |
-
},
|
435 |
-
"127": {
|
436 |
-
"content": "ỵ",
|
437 |
-
"lstrip": false,
|
438 |
-
"normalized": true,
|
439 |
-
"rstrip": false,
|
440 |
-
"single_word": false,
|
441 |
-
"special": false
|
442 |
-
},
|
443 |
-
"128": {
|
444 |
-
"content": "ế",
|
445 |
-
"lstrip": false,
|
446 |
-
"normalized": true,
|
447 |
-
"rstrip": false,
|
448 |
-
"single_word": false,
|
449 |
-
"special": false
|
450 |
-
},
|
451 |
-
"129": {
|
452 |
-
"content": "ề",
|
453 |
-
"lstrip": false,
|
454 |
-
"normalized": true,
|
455 |
-
"rstrip": false,
|
456 |
-
"single_word": false,
|
457 |
-
"special": false
|
458 |
-
},
|
459 |
-
"130": {
|
460 |
-
"content": "ể",
|
461 |
-
"lstrip": false,
|
462 |
-
"normalized": true,
|
463 |
-
"rstrip": false,
|
464 |
-
"single_word": false,
|
465 |
-
"special": false
|
466 |
-
},
|
467 |
-
"131": {
|
468 |
-
"content": "ễ",
|
469 |
-
"lstrip": false,
|
470 |
-
"normalized": true,
|
471 |
-
"rstrip": false,
|
472 |
-
"single_word": false,
|
473 |
-
"special": false
|
474 |
-
},
|
475 |
-
"132": {
|
476 |
-
"content": "ệ",
|
477 |
-
"lstrip": false,
|
478 |
-
"normalized": true,
|
479 |
-
"rstrip": false,
|
480 |
-
"single_word": false,
|
481 |
-
"special": false
|
482 |
-
},
|
483 |
-
"133": {
|
484 |
-
"content": "ứ",
|
485 |
-
"lstrip": false,
|
486 |
-
"normalized": true,
|
487 |
-
"rstrip": false,
|
488 |
-
"single_word": false,
|
489 |
-
"special": false
|
490 |
-
},
|
491 |
-
"134": {
|
492 |
-
"content": "ừ",
|
493 |
-
"lstrip": false,
|
494 |
-
"normalized": true,
|
495 |
-
"rstrip": false,
|
496 |
-
"single_word": false,
|
497 |
-
"special": false
|
498 |
-
},
|
499 |
-
"135": {
|
500 |
-
"content": "ử",
|
501 |
-
"lstrip": false,
|
502 |
-
"normalized": true,
|
503 |
-
"rstrip": false,
|
504 |
-
"single_word": false,
|
505 |
-
"special": false
|
506 |
-
},
|
507 |
-
"136": {
|
508 |
-
"content": "ữ",
|
509 |
-
"lstrip": false,
|
510 |
-
"normalized": true,
|
511 |
-
"rstrip": false,
|
512 |
-
"single_word": false,
|
513 |
-
"special": false
|
514 |
-
},
|
515 |
-
"137": {
|
516 |
-
"content": "ự",
|
517 |
-
"lstrip": false,
|
518 |
-
"normalized": true,
|
519 |
-
"rstrip": false,
|
520 |
-
"single_word": false,
|
521 |
-
"special": false
|
522 |
-
},
|
523 |
-
"138": {
|
524 |
-
"content": "ư",
|
525 |
-
"lstrip": false,
|
526 |
-
"normalized": true,
|
527 |
-
"rstrip": false,
|
528 |
-
"single_word": false,
|
529 |
-
"special": false
|
530 |
-
},
|
531 |
-
"139": {
|
532 |
-
"content": "ú",
|
533 |
-
"lstrip": false,
|
534 |
-
"normalized": true,
|
535 |
-
"rstrip": false,
|
536 |
-
"single_word": false,
|
537 |
-
"special": false
|
538 |
-
},
|
539 |
-
"140": {
|
540 |
-
"content": "ù",
|
541 |
-
"lstrip": false,
|
542 |
-
"normalized": true,
|
543 |
-
"rstrip": false,
|
544 |
-
"single_word": false,
|
545 |
-
"special": false
|
546 |
-
},
|
547 |
-
"141": {
|
548 |
-
"content": "ủ",
|
549 |
-
"lstrip": false,
|
550 |
-
"normalized": true,
|
551 |
-
"rstrip": false,
|
552 |
-
"single_word": false,
|
553 |
-
"special": false
|
554 |
-
},
|
555 |
-
"142": {
|
556 |
-
"content": "ũ",
|
557 |
-
"lstrip": false,
|
558 |
-
"normalized": true,
|
559 |
-
"rstrip": false,
|
560 |
-
"single_word": false,
|
561 |
-
"special": false
|
562 |
-
},
|
563 |
-
"143": {
|
564 |
-
"content": "ụ",
|
565 |
-
"lstrip": false,
|
566 |
-
"normalized": true,
|
567 |
-
"rstrip": false,
|
568 |
-
"single_word": false,
|
569 |
-
"special": false
|
570 |
-
},
|
571 |
-
"144": {
|
572 |
-
"content": "đ",
|
573 |
-
"lstrip": false,
|
574 |
-
"normalized": true,
|
575 |
-
"rstrip": false,
|
576 |
-
"single_word": false,
|
577 |
-
"special": false
|
578 |
-
},
|
579 |
-
"145": {
|
580 |
-
"content": "1",
|
581 |
-
"lstrip": false,
|
582 |
-
"normalized": true,
|
583 |
-
"rstrip": false,
|
584 |
-
"single_word": false,
|
585 |
-
"special": false
|
586 |
-
},
|
587 |
-
"146": {
|
588 |
-
"content": "2",
|
589 |
-
"lstrip": false,
|
590 |
-
"normalized": true,
|
591 |
-
"rstrip": false,
|
592 |
-
"single_word": false,
|
593 |
-
"special": false
|
594 |
-
},
|
595 |
-
"147": {
|
596 |
-
"content": "3",
|
597 |
-
"lstrip": false,
|
598 |
-
"normalized": true,
|
599 |
-
"rstrip": false,
|
600 |
-
"single_word": false,
|
601 |
-
"special": false
|
602 |
-
},
|
603 |
-
"148": {
|
604 |
-
"content": "4",
|
605 |
-
"lstrip": false,
|
606 |
-
"normalized": true,
|
607 |
-
"rstrip": false,
|
608 |
-
"single_word": false,
|
609 |
-
"special": false
|
610 |
-
},
|
611 |
-
"149": {
|
612 |
-
"content": "5",
|
613 |
-
"lstrip": false,
|
614 |
-
"normalized": true,
|
615 |
-
"rstrip": false,
|
616 |
-
"single_word": false,
|
617 |
-
"special": false
|
618 |
-
},
|
619 |
-
"150": {
|
620 |
-
"content": "6",
|
621 |
-
"lstrip": false,
|
622 |
-
"normalized": true,
|
623 |
-
"rstrip": false,
|
624 |
-
"single_word": false,
|
625 |
-
"special": false
|
626 |
-
},
|
627 |
-
"151": {
|
628 |
-
"content": "7",
|
629 |
-
"lstrip": false,
|
630 |
-
"normalized": true,
|
631 |
-
"rstrip": false,
|
632 |
-
"single_word": false,
|
633 |
-
"special": false
|
634 |
-
},
|
635 |
-
"152": {
|
636 |
-
"content": "8",
|
637 |
-
"lstrip": false,
|
638 |
-
"normalized": true,
|
639 |
-
"rstrip": false,
|
640 |
-
"single_word": false,
|
641 |
-
"special": false
|
642 |
-
},
|
643 |
-
"153": {
|
644 |
-
"content": "9",
|
645 |
-
"lstrip": false,
|
646 |
-
"normalized": true,
|
647 |
-
"rstrip": false,
|
648 |
-
"single_word": false,
|
649 |
-
"special": false
|
650 |
-
},
|
651 |
-
"154": {
|
652 |
-
"content": "0",
|
653 |
-
"lstrip": false,
|
654 |
-
"normalized": true,
|
655 |
-
"rstrip": false,
|
656 |
-
"single_word": false,
|
657 |
-
"special": false
|
658 |
-
},
|
659 |
-
"155": {
|
660 |
-
"content": " ",
|
661 |
-
"lstrip": false,
|
662 |
-
"normalized": true,
|
663 |
-
"rstrip": false,
|
664 |
-
"single_word": false,
|
665 |
-
"special": false
|
666 |
-
}
|
667 |
-
},
|
668 |
-
"bos_token": "<s>",
|
669 |
-
"clean_up_tokenization_spaces": false,
|
670 |
-
"eos_token": "</s>",
|
671 |
-
"extra_special_tokens": {},
|
672 |
-
"mask_token": "<mask>",
|
673 |
-
"model_max_length": 600,
|
674 |
-
"normalize": false,
|
675 |
-
"pad_token": "<pad>",
|
676 |
-
"processor_class": "SpeechT5Processor",
|
677 |
-
"sp_model_kwargs": {},
|
678 |
-
"tokenizer_class": "SpeechT5Tokenizer",
|
679 |
-
"unk_token": "<unk>"
|
680 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
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": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"73": {
|
36 |
+
"content": "é",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": false
|
42 |
+
},
|
43 |
+
"76": {
|
44 |
+
"content": "ê",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"79": {
|
52 |
+
"content": "<mask>",
|
53 |
+
"lstrip": true,
|
54 |
+
"normalized": true,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"80": {
|
60 |
+
"content": "<ctc_blank>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
},
|
67 |
+
"81": {
|
68 |
+
"content": "á",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": true,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"82": {
|
76 |
+
"content": "à",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": true,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"83": {
|
84 |
+
"content": "ạ",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": true,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"84": {
|
92 |
+
"content": "ả",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": true,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"85": {
|
100 |
+
"content": "ã",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": true,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
},
|
107 |
+
"86": {
|
108 |
+
"content": "â",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": true,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": false
|
114 |
+
},
|
115 |
+
"87": {
|
116 |
+
"content": "ẩ",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": true,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": false
|
122 |
+
},
|
123 |
+
"88": {
|
124 |
+
"content": "ấ",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": true,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": false
|
130 |
+
},
|
131 |
+
"89": {
|
132 |
+
"content": "ầ",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": true,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": false
|
138 |
+
},
|
139 |
+
"90": {
|
140 |
+
"content": "ậ",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": true,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": false
|
146 |
+
},
|
147 |
+
"91": {
|
148 |
+
"content": "ẫ",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": true,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": false
|
154 |
+
},
|
155 |
+
"92": {
|
156 |
+
"content": "ă",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": true,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": false
|
162 |
+
},
|
163 |
+
"93": {
|
164 |
+
"content": "ắ",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": true,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": false
|
170 |
+
},
|
171 |
+
"94": {
|
172 |
+
"content": "ằ",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": true,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": false
|
178 |
+
},
|
179 |
+
"95": {
|
180 |
+
"content": "ặ",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": true,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": false
|
186 |
+
},
|
187 |
+
"96": {
|
188 |
+
"content": "ẳ",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": true,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": false
|
194 |
+
},
|
195 |
+
"97": {
|
196 |
+
"content": "è",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": true,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": false
|
202 |
+
},
|
203 |
+
"98": {
|
204 |
+
"content": "ẻ",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": true,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": false
|
210 |
+
},
|
211 |
+
"99": {
|
212 |
+
"content": "ẽ",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": true,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": false
|
218 |
+
},
|
219 |
+
"100": {
|
220 |
+
"content": "ẹ",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": true,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": false
|
226 |
+
},
|
227 |
+
"101": {
|
228 |
+
"content": "ó",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": true,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": false
|
234 |
+
},
|
235 |
+
"102": {
|
236 |
+
"content": "ò",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": true,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": false
|
242 |
+
},
|
243 |
+
"103": {
|
244 |
+
"content": "ỏ",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": true,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": false
|
250 |
+
},
|
251 |
+
"104": {
|
252 |
+
"content": "õ",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": true,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": false
|
258 |
+
},
|
259 |
+
"105": {
|
260 |
+
"content": "ọ",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": true,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": false
|
266 |
+
},
|
267 |
+
"106": {
|
268 |
+
"content": "ố",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": true,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": false
|
274 |
+
},
|
275 |
+
"107": {
|
276 |
+
"content": "ồ",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": true,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": false
|
282 |
+
},
|
283 |
+
"108": {
|
284 |
+
"content": "ỗ",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": true,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": false
|
290 |
+
},
|
291 |
+
"109": {
|
292 |
+
"content": "ổ",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": true,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": false
|
298 |
+
},
|
299 |
+
"110": {
|
300 |
+
"content": "ộ",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": true,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": false
|
306 |
+
},
|
307 |
+
"111": {
|
308 |
+
"content": "ô",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": true,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": false
|
314 |
+
},
|
315 |
+
"112": {
|
316 |
+
"content": "ớ",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": true,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": false
|
322 |
+
},
|
323 |
+
"113": {
|
324 |
+
"content": "ờ",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": true,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": false
|
330 |
+
},
|
331 |
+
"114": {
|
332 |
+
"content": "ở",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": true,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": false
|
338 |
+
},
|
339 |
+
"115": {
|
340 |
+
"content": "ỡ",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": true,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": false
|
346 |
+
},
|
347 |
+
"116": {
|
348 |
+
"content": "ợ",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": true,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": false
|
354 |
+
},
|
355 |
+
"117": {
|
356 |
+
"content": "ơ",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": true,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": false
|
362 |
+
},
|
363 |
+
"118": {
|
364 |
+
"content": "í",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": true,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": false
|
370 |
+
},
|
371 |
+
"119": {
|
372 |
+
"content": "ì",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": true,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": false
|
378 |
+
},
|
379 |
+
"120": {
|
380 |
+
"content": "ị",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": true,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": false
|
386 |
+
},
|
387 |
+
"121": {
|
388 |
+
"content": "ĩ",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": true,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": false
|
394 |
+
},
|
395 |
+
"122": {
|
396 |
+
"content": "ỉ",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": true,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": false
|
402 |
+
},
|
403 |
+
"123": {
|
404 |
+
"content": "ý",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": true,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": false
|
410 |
+
},
|
411 |
+
"124": {
|
412 |
+
"content": "ỳ",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": true,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": false
|
418 |
+
},
|
419 |
+
"125": {
|
420 |
+
"content": "ỷ",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": true,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": false
|
426 |
+
},
|
427 |
+
"126": {
|
428 |
+
"content": "ỹ",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": true,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": false
|
434 |
+
},
|
435 |
+
"127": {
|
436 |
+
"content": "ỵ",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": true,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": false
|
442 |
+
},
|
443 |
+
"128": {
|
444 |
+
"content": "ế",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": true,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": false
|
450 |
+
},
|
451 |
+
"129": {
|
452 |
+
"content": "ề",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": true,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": false
|
458 |
+
},
|
459 |
+
"130": {
|
460 |
+
"content": "ể",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": true,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": false
|
466 |
+
},
|
467 |
+
"131": {
|
468 |
+
"content": "ễ",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": true,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": false
|
474 |
+
},
|
475 |
+
"132": {
|
476 |
+
"content": "ệ",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": true,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": false
|
482 |
+
},
|
483 |
+
"133": {
|
484 |
+
"content": "ứ",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": true,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": false
|
490 |
+
},
|
491 |
+
"134": {
|
492 |
+
"content": "ừ",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": true,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": false
|
498 |
+
},
|
499 |
+
"135": {
|
500 |
+
"content": "ử",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": true,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": false
|
506 |
+
},
|
507 |
+
"136": {
|
508 |
+
"content": "ữ",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": true,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": false
|
514 |
+
},
|
515 |
+
"137": {
|
516 |
+
"content": "ự",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": true,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": false
|
522 |
+
},
|
523 |
+
"138": {
|
524 |
+
"content": "ư",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": true,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": false
|
530 |
+
},
|
531 |
+
"139": {
|
532 |
+
"content": "ú",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": true,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": false
|
538 |
+
},
|
539 |
+
"140": {
|
540 |
+
"content": "ù",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": true,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": false
|
546 |
+
},
|
547 |
+
"141": {
|
548 |
+
"content": "ủ",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": true,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": false
|
554 |
+
},
|
555 |
+
"142": {
|
556 |
+
"content": "ũ",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": true,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": false
|
562 |
+
},
|
563 |
+
"143": {
|
564 |
+
"content": "ụ",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": true,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": false
|
570 |
+
},
|
571 |
+
"144": {
|
572 |
+
"content": "đ",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": true,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": false
|
578 |
+
},
|
579 |
+
"145": {
|
580 |
+
"content": "1",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": true,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": false
|
586 |
+
},
|
587 |
+
"146": {
|
588 |
+
"content": "2",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": true,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": false
|
594 |
+
},
|
595 |
+
"147": {
|
596 |
+
"content": "3",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": true,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": false
|
602 |
+
},
|
603 |
+
"148": {
|
604 |
+
"content": "4",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": true,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": false
|
610 |
+
},
|
611 |
+
"149": {
|
612 |
+
"content": "5",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": true,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": false
|
618 |
+
},
|
619 |
+
"150": {
|
620 |
+
"content": "6",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": true,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": false
|
626 |
+
},
|
627 |
+
"151": {
|
628 |
+
"content": "7",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": true,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": false
|
634 |
+
},
|
635 |
+
"152": {
|
636 |
+
"content": "8",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": true,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": false
|
642 |
+
},
|
643 |
+
"153": {
|
644 |
+
"content": "9",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": true,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": false
|
650 |
+
},
|
651 |
+
"154": {
|
652 |
+
"content": "0",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": true,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": false
|
658 |
+
},
|
659 |
+
"155": {
|
660 |
+
"content": " ",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": true,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": false
|
666 |
+
}
|
667 |
+
},
|
668 |
+
"bos_token": "<s>",
|
669 |
+
"clean_up_tokenization_spaces": false,
|
670 |
+
"eos_token": "</s>",
|
671 |
+
"extra_special_tokens": {},
|
672 |
+
"mask_token": "<mask>",
|
673 |
+
"model_max_length": 600,
|
674 |
+
"normalize": false,
|
675 |
+
"pad_token": "<pad>",
|
676 |
+
"processor_class": "SpeechT5Processor",
|
677 |
+
"sp_model_kwargs": {},
|
678 |
+
"tokenizer_class": "SpeechT5Tokenizer",
|
679 |
+
"unk_token": "<unk>"
|
680 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:800212317d11b9ccc4d2b687f7ea23c13424dc1ca64616fd7fea8aef8f013f6d
|
3 |
+
size 5560
|