hts98 commited on
Commit
764c540
1 Parent(s): ce4bac8

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 109,
3
+ "<s>": 108
4
+ }
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mms-300m",
3
+ "activation_dropout": 0.0,
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": 0.0,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 768,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
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": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
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,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.05,
69
+ "model_type": "wav2vec2",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 16,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
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,
84
+ 2,
85
+ 3,
86
+ 1,
87
+ 1
88
+ ],
89
+ "tdnn_dim": [
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 1500
95
+ ],
96
+ "tdnn_kernel": [
97
+ 5,
98
+ 3,
99
+ 3,
100
+ 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 ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7875ed834e89dc78e56a01fa5a04ea5b3b932da602f08b3a1bba0eabfc731621
3
+ size 1262352813
runs/Jul01_06-27-25_e151b5d50473/events.out.tfevents.1688193292.e151b5d50473.15743.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52abaae4171125dff1123d17d2f1c7ecae5d69bbd01f8a2a3c01056f177e79b1
3
+ size 5754
special_tokens_map.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "content": "<s>",
33
+ "lstrip": false,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "</s>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ }
45
+ ],
46
+ "bos_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "pad_token": "[PAD]",
49
+ "unk_token": "[UNK]"
50
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
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",
12
+ "unk_token": "[UNK]",
13
+ "word_delimiter_token": "|"
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:264262fec90156f1b21d16e31e2eb9afcdf930a65fe4b8020f6f8a3becbcd147
3
+ size 4027
vocab.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }