excalibur12 commited on
Commit
bf30082
1 Parent(s): 3fe9676

Training in progress, step 1000

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 65,
3
+ "<s>": 64
4
+ }
config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForCTC"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.0,
62
+ "mask_channel_length": 10,
63
+ "mask_channel_min_space": 1,
64
+ "mask_channel_other": 0.0,
65
+ "mask_channel_prob": 0.0,
66
+ "mask_channel_selection": "static",
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_min_space": 1,
73
+ "mask_time_other": 0.0,
74
+ "mask_time_prob": 0.05,
75
+ "mask_time_selection": "static",
76
+ "model_type": "wav2vec2",
77
+ "no_mask_channel_overlap": false,
78
+ "no_mask_time_overlap": false,
79
+ "num_adapter_layers": 3,
80
+ "num_attention_heads": 12,
81
+ "num_codevector_groups": 2,
82
+ "num_codevectors_per_group": 320,
83
+ "num_conv_pos_embedding_groups": 16,
84
+ "num_conv_pos_embeddings": 128,
85
+ "num_feat_extract_layers": 7,
86
+ "num_hidden_layers": 12,
87
+ "num_negatives": 100,
88
+ "output_hidden_size": 768,
89
+ "pad_token_id": 63,
90
+ "proj_codevector_dim": 256,
91
+ "tdnn_dilation": [
92
+ 1,
93
+ 2,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tdnn_dim": [
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 1500
104
+ ],
105
+ "tdnn_kernel": [
106
+ 5,
107
+ 3,
108
+ 3,
109
+ 1,
110
+ 1
111
+ ],
112
+ "torch_dtype": "float32",
113
+ "transformers_version": "4.28.1",
114
+ "use_weighted_layer_sum": false,
115
+ "vocab_size": 66,
116
+ "xvector_output_dim": 512
117
+ }
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": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": false,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14f4b1c8ba6f782cc492e32b5420fd1bb42e3a47548c38cb218a5a9e8e215826
3
+ size 377763361
runs/Apr01_01-58-30_oem-System-Product-Name/1711904363.4600396/events.out.tfevents.1711904363.oem-System-Product-Name.120112.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55077e802094e137535983fe175ee78b98d715ddfdf456cd4c9888cd2d6567d9
3
+ size 5986
runs/Apr01_01-58-30_oem-System-Product-Name/events.out.tfevents.1711904363.oem-System-Product-Name.120112.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a6b9ae72689af8e99358d171352ee174d542997ad8d58cd72af229297bbdc67
3
+ size 6259
special_tokens_map.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
19
+ "eos_token": "</s>",
20
+ "pad_token": "[PAD]",
21
+ "unk_token": "[UNK]"
22
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_phonemize": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "phone_delimiter_token": "|",
9
+ "phonemizer_backend": "espeak",
10
+ "phonemizer_lang": "en-us",
11
+ "processor_class": "Wav2Vec2Processor",
12
+ "tokenizer_class": "Wav2Vec2PhonemeCTCTokenizer",
13
+ "unk_token": "[UNK]",
14
+ "word_delimiter_token": null
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ae34888490feece1130bba27ac7a4ce3982307e4495c0e94154c54fc78946c4
3
+ size 3643
vocab.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 63,
3
+ "[UNK]": 62,
4
+ "aa": 0,
5
+ "ae": 1,
6
+ "ah": 2,
7
+ "ao": 3,
8
+ "aw": 4,
9
+ "ax": 5,
10
+ "ax-h": 6,
11
+ "axr": 7,
12
+ "ay": 8,
13
+ "b": 9,
14
+ "bcl": 10,
15
+ "ch": 11,
16
+ "d": 12,
17
+ "dcl": 13,
18
+ "dh": 14,
19
+ "dx": 15,
20
+ "eh": 16,
21
+ "el": 17,
22
+ "em": 18,
23
+ "en": 19,
24
+ "eng": 20,
25
+ "epi": 21,
26
+ "er": 22,
27
+ "ey": 23,
28
+ "f": 24,
29
+ "g": 25,
30
+ "gcl": 26,
31
+ "h#": 27,
32
+ "hh": 28,
33
+ "hv": 29,
34
+ "ih": 30,
35
+ "ix": 31,
36
+ "iy": 32,
37
+ "jh": 33,
38
+ "k": 34,
39
+ "kcl": 35,
40
+ "l": 36,
41
+ "m": 37,
42
+ "n": 38,
43
+ "ng": 39,
44
+ "nx": 40,
45
+ "ow": 41,
46
+ "oy": 42,
47
+ "p": 43,
48
+ "pau": 44,
49
+ "pcl": 45,
50
+ "q": 46,
51
+ "r": 47,
52
+ "s": 48,
53
+ "sh": 49,
54
+ "t": 50,
55
+ "tcl": 51,
56
+ "th": 52,
57
+ "uh": 53,
58
+ "uw": 54,
59
+ "ux": 55,
60
+ "v": 56,
61
+ "w": 57,
62
+ "y": 58,
63
+ "z": 59,
64
+ "zh": 60,
65
+ "|": 61
66
+ }