Training in progress, epoch 1
Browse files- added_tokens.json +4 -0
- config.json +6 -7
- preprocessor_config.json +2 -1
- pytorch_model.bin +2 -2
- runs/Jun30_10-04-05_64df48378bb2/events.out.tfevents.1688120414.64df48378bb2.1419.0 +3 -0
- special_tokens_map.json +30 -0
- tokenizer_config.json +1 -0
- training_args.bin +2 -2
- vocab.json +107 -105
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 109,
|
3 |
+
"<s>": 108
|
4 |
+
}
|
config.json
CHANGED
@@ -9,7 +9,7 @@
|
|
9 |
"architectures": [
|
10 |
"Wav2Vec2ForCTC"
|
11 |
],
|
12 |
-
"attention_dropout": 0.
|
13 |
"bos_token_id": 1,
|
14 |
"classifier_proj_size": 256,
|
15 |
"codevector_dim": 768,
|
@@ -53,14 +53,13 @@
|
|
53 |
"feat_proj_dropout": 0.0,
|
54 |
"feat_quantizer_dropout": 0.0,
|
55 |
"final_dropout": 0.0,
|
56 |
-
"gradient_checkpointing": false,
|
57 |
"hidden_act": "gelu",
|
58 |
-
"hidden_dropout": 0.
|
59 |
"hidden_size": 1024,
|
60 |
"initializer_range": 0.02,
|
61 |
"intermediate_size": 4096,
|
62 |
"layer_norm_eps": 1e-05,
|
63 |
-
"layerdrop": 0.
|
64 |
"mask_feature_length": 10,
|
65 |
"mask_feature_min_masks": 0,
|
66 |
"mask_feature_prob": 0.0,
|
@@ -78,7 +77,7 @@
|
|
78 |
"num_hidden_layers": 24,
|
79 |
"num_negatives": 100,
|
80 |
"output_hidden_size": 1024,
|
81 |
-
"pad_token_id":
|
82 |
"proj_codevector_dim": 768,
|
83 |
"tdnn_dilation": [
|
84 |
1,
|
@@ -102,8 +101,8 @@
|
|
102 |
1
|
103 |
],
|
104 |
"torch_dtype": "float32",
|
105 |
-
"transformers_version": "4.
|
106 |
"use_weighted_layer_sum": false,
|
107 |
-
"vocab_size":
|
108 |
"xvector_output_dim": 512
|
109 |
}
|
|
|
9 |
"architectures": [
|
10 |
"Wav2Vec2ForCTC"
|
11 |
],
|
12 |
+
"attention_dropout": 0.0,
|
13 |
"bos_token_id": 1,
|
14 |
"classifier_proj_size": 256,
|
15 |
"codevector_dim": 768,
|
|
|
53 |
"feat_proj_dropout": 0.0,
|
54 |
"feat_quantizer_dropout": 0.0,
|
55 |
"final_dropout": 0.0,
|
|
|
56 |
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.0,
|
58 |
"hidden_size": 1024,
|
59 |
"initializer_range": 0.02,
|
60 |
"intermediate_size": 4096,
|
61 |
"layer_norm_eps": 1e-05,
|
62 |
+
"layerdrop": 0.0,
|
63 |
"mask_feature_length": 10,
|
64 |
"mask_feature_min_masks": 0,
|
65 |
"mask_feature_prob": 0.0,
|
|
|
77 |
"num_hidden_layers": 24,
|
78 |
"num_negatives": 100,
|
79 |
"output_hidden_size": 1024,
|
80 |
+
"pad_token_id": 107,
|
81 |
"proj_codevector_dim": 768,
|
82 |
"tdnn_dilation": [
|
83 |
1,
|
|
|
101 |
1
|
102 |
],
|
103 |
"torch_dtype": "float32",
|
104 |
+
"transformers_version": "4.31.0.dev0",
|
105 |
"use_weighted_layer_sum": false,
|
106 |
+
"vocab_size": 110,
|
107 |
"xvector_output_dim": 512
|
108 |
}
|
preprocessor_config.json
CHANGED
@@ -3,7 +3,8 @@
|
|
3 |
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
-
"padding_value": 0
|
|
|
7 |
"return_attention_mask": true,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
|
|
3 |
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
+
"padding_value": 0,
|
7 |
+
"processor_class": "Wav2Vec2Processor",
|
8 |
"return_attention_mask": true,
|
9 |
"sampling_rate": 16000
|
10 |
}
|
pytorch_model.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 sha256:6f659c9a20b5d330d5b73a45c71b0e1becf93e1349578ac3a304019af8afbcfb
|
3 |
+
size 1262352813
|
runs/Jun30_10-04-05_64df48378bb2/events.out.tfevents.1688120414.64df48378bb2.1419.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:018882fbff9f0b0de67d1635e3c4e7cce04fd3814968bdcdb421927f854516ef
|
3 |
+
size 5845
|
special_tokens_map.json
CHANGED
@@ -1,4 +1,34 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"eos_token": "</s>",
|
4 |
"pad_token": "[PAD]",
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "</s>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"content": "<s>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"content": "</s>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": true,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
],
|
32 |
"bos_token": "<s>",
|
33 |
"eos_token": "</s>",
|
34 |
"pad_token": "[PAD]",
|
tokenizer_config.json
CHANGED
@@ -5,6 +5,7 @@
|
|
5 |
"eos_token": "</s>",
|
6 |
"model_max_length": 1000000000000000019884624838656,
|
7 |
"pad_token": "[PAD]",
|
|
|
8 |
"replace_word_delimiter_char": " ",
|
9 |
"target_lang": null,
|
10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
5 |
"eos_token": "</s>",
|
6 |
"model_max_length": 1000000000000000019884624838656,
|
7 |
"pad_token": "[PAD]",
|
8 |
+
"processor_class": "Wav2Vec2Processor",
|
9 |
"replace_word_delimiter_char": " ",
|
10 |
"target_lang": null,
|
11 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
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 sha256:645a14c785ae828345ed6de887448e019cdae478f8e4270b5aa6a6943e08281f
|
3 |
+
size 4027
|
vocab.json
CHANGED
@@ -1,108 +1,110 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
|
|
|
|
49 |
"í": 47,
|
50 |
-
"ò":
|
51 |
-
"ó":
|
52 |
-
"ô":
|
53 |
-
"õ":
|
54 |
-
"ù":
|
55 |
-
"ú":
|
56 |
-
"ý":
|
57 |
-
"ă":
|
58 |
-
"đ":
|
59 |
-
"ĩ":
|
60 |
-
"ũ":
|
61 |
-
"ơ":
|
62 |
-
"ư":
|
63 |
-
"ạ":
|
64 |
-
"ả":
|
65 |
-
"ấ":
|
66 |
-
"ầ":
|
67 |
-
"ẩ":
|
68 |
-
"ẫ":
|
69 |
-
"ậ":
|
70 |
-
"ắ":
|
71 |
-
"ằ":
|
72 |
-
"ẳ":
|
73 |
-
"ẵ":
|
74 |
-
"ặ":
|
75 |
-
"ẹ":
|
76 |
-
"ẻ":
|
77 |
-
"ẽ":
|
78 |
-
"ế":
|
79 |
-
"ề":
|
80 |
-
"ể":
|
81 |
-
"ễ":
|
82 |
-
"ệ":
|
83 |
-
"ỉ":
|
84 |
-
"ị":
|
85 |
-
"ọ":
|
86 |
-
"ỏ":
|
87 |
-
"ố":
|
88 |
-
"ồ":
|
89 |
-
"ổ":
|
90 |
-
"ỗ":
|
91 |
-
"ộ":
|
92 |
-
"ớ":
|
93 |
-
"ờ":
|
94 |
-
"ở":
|
95 |
-
"ỡ":
|
96 |
-
"ợ":
|
97 |
-
"ụ":
|
98 |
-
"ủ":
|
99 |
-
"ứ":
|
100 |
-
"ừ":
|
101 |
-
"ử":
|
102 |
-
"ữ":
|
103 |
-
"ự":
|
104 |
-
"ỳ":
|
105 |
-
"ỷ":
|
106 |
-
"ỹ":
|
107 |
-
"₫":
|
108 |
}
|
|
|
1 |
{
|
2 |
+
",": 1,
|
3 |
+
".": 2,
|
4 |
+
"0": 3,
|
5 |
+
"1": 4,
|
6 |
+
"2": 5,
|
7 |
+
"3": 6,
|
8 |
+
"4": 7,
|
9 |
+
"5": 8,
|
10 |
+
"6": 9,
|
11 |
+
"7": 10,
|
12 |
+
"8": 11,
|
13 |
+
"9": 12,
|
14 |
+
"[PAD]": 107,
|
15 |
+
"[UNK]": 106,
|
16 |
+
"a": 13,
|
17 |
+
"b": 14,
|
18 |
+
"c": 15,
|
19 |
+
"d": 16,
|
20 |
+
"e": 17,
|
21 |
+
"f": 18,
|
22 |
+
"g": 19,
|
23 |
+
"h": 20,
|
24 |
+
"i": 21,
|
25 |
+
"j": 22,
|
26 |
+
"k": 23,
|
27 |
+
"l": 24,
|
28 |
+
"m": 25,
|
29 |
+
"n": 26,
|
30 |
+
"o": 27,
|
31 |
+
"p": 28,
|
32 |
+
"q": 29,
|
33 |
+
"r": 30,
|
34 |
+
"s": 31,
|
35 |
+
"t": 32,
|
36 |
+
"u": 33,
|
37 |
+
"v": 34,
|
38 |
+
"w": 35,
|
39 |
+
"x": 36,
|
40 |
+
"y": 37,
|
41 |
+
"z": 38,
|
42 |
+
"|": 0,
|
43 |
+
"à": 39,
|
44 |
+
"á": 40,
|
45 |
+
"â": 41,
|
46 |
+
"ã": 42,
|
47 |
+
"è": 43,
|
48 |
+
"é": 44,
|
49 |
+
"ê": 45,
|
50 |
+
"ì": 46,
|
51 |
"í": 47,
|
52 |
+
"ò": 48,
|
53 |
+
"ó": 49,
|
54 |
+
"ô": 50,
|
55 |
+
"õ": 51,
|
56 |
+
"ù": 52,
|
57 |
+
"ú": 53,
|
58 |
+
"ý": 54,
|
59 |
+
"ă": 55,
|
60 |
+
"đ": 56,
|
61 |
+
"ĩ": 57,
|
62 |
+
"ũ": 58,
|
63 |
+
"ơ": 59,
|
64 |
+
"ư": 60,
|
65 |
+
"ạ": 61,
|
66 |
+
"ả": 62,
|
67 |
+
"ấ": 63,
|
68 |
+
"ầ": 64,
|
69 |
+
"ẩ": 65,
|
70 |
+
"ẫ": 66,
|
71 |
+
"ậ": 67,
|
72 |
+
"ắ": 68,
|
73 |
+
"ằ": 69,
|
74 |
+
"ẳ": 70,
|
75 |
+
"ẵ": 71,
|
76 |
+
"ặ": 72,
|
77 |
+
"ẹ": 73,
|
78 |
+
"ẻ": 74,
|
79 |
+
"ẽ": 75,
|
80 |
+
"ế": 76,
|
81 |
+
"ề": 77,
|
82 |
+
"ể": 78,
|
83 |
+
"ễ": 79,
|
84 |
+
"ệ": 80,
|
85 |
+
"ỉ": 81,
|
86 |
+
"ị": 82,
|
87 |
+
"ọ": 83,
|
88 |
+
"ỏ": 84,
|
89 |
+
"ố": 85,
|
90 |
+
"ồ": 86,
|
91 |
+
"ổ": 87,
|
92 |
+
"ỗ": 88,
|
93 |
+
"ộ": 89,
|
94 |
+
"ớ": 90,
|
95 |
+
"ờ": 91,
|
96 |
+
"ở": 92,
|
97 |
+
"ỡ": 93,
|
98 |
+
"ợ": 94,
|
99 |
+
"ụ": 95,
|
100 |
+
"ủ": 96,
|
101 |
+
"ứ": 97,
|
102 |
+
"ừ": 98,
|
103 |
+
"ử": 99,
|
104 |
+
"ữ": 100,
|
105 |
+
"ự": 101,
|
106 |
+
"ỳ": 102,
|
107 |
+
"ỷ": 103,
|
108 |
+
"ỹ": 104,
|
109 |
+
"₫": 105
|
110 |
}
|