stimothy77
commited on
Commit
•
a1f25e3
1
Parent(s):
3f6bef6
Training in progress, step 1
Browse files- config.json +118 -0
- model.safetensors +3 -0
- preprocessor_config.json +10 -0
- runs/Dec12_04-21-48_fe35c24a6b04/events.out.tfevents.1702354914.fe35c24a6b04.4020.0 +3 -0
- runs/Dec12_04-39-47_fe35c24a6b04/events.out.tfevents.1702355989.fe35c24a6b04.4020.1 +3 -0
- runs/Dec12_04-43-19_fe35c24a6b04/events.out.tfevents.1702356201.fe35c24a6b04.4020.2 +3 -0
- runs/Dec12_04-44-22_fe35c24a6b04/events.out.tfevents.1702356263.fe35c24a6b04.4020.3 +3 -0
- runs/Dec12_04-45-17_fe35c24a6b04/events.out.tfevents.1702356318.fe35c24a6b04.4020.4 +3 -0
- runs/Dec12_04-51-48_fe35c24a6b04/events.out.tfevents.1702356709.fe35c24a6b04.4020.5 +3 -0
- runs/Dec12_04-58-27_fe35c24a6b04/events.out.tfevents.1702357111.fe35c24a6b04.4020.6 +3 -0
- runs/Dec12_04-59-52_fe35c24a6b04/events.out.tfevents.1702357201.fe35c24a6b04.4020.7 +3 -0
- runs/Dec12_05-06-53_fe35c24a6b04/events.out.tfevents.1702357617.fe35c24a6b04.4020.8 +3 -0
- runs/Dec12_05-13-06_fe35c24a6b04/events.out.tfevents.1702357991.fe35c24a6b04.4020.9 +3 -0
- runs/Dec12_05-28-37_fe35c24a6b04/events.out.tfevents.1702358922.fe35c24a6b04.22147.0 +3 -0
- runs/Dec12_05-38-57_fe35c24a6b04/events.out.tfevents.1702359547.fe35c24a6b04.22147.1 +3 -0
- runs/Dec12_05-42-45_fe35c24a6b04/events.out.tfevents.1702359774.fe35c24a6b04.22147.2 +3 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +50 -0
- training_args.bin +3 -0
- vocab.json +34 -0
config.json
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
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": 0.1,
|
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_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.0,
|
55 |
+
"freeze_feat_extract_train": true,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_size": 768,
|
59 |
+
"initializer_range": 0.02,
|
60 |
+
"intermediate_size": 3072,
|
61 |
+
"layer_norm_eps": 1e-05,
|
62 |
+
"layerdrop": 0.0,
|
63 |
+
"mask_channel_length": 10,
|
64 |
+
"mask_channel_min_space": 1,
|
65 |
+
"mask_channel_other": 0.0,
|
66 |
+
"mask_channel_prob": 0.0,
|
67 |
+
"mask_channel_selection": "static",
|
68 |
+
"mask_feature_length": 10,
|
69 |
+
"mask_feature_min_masks": 0,
|
70 |
+
"mask_feature_prob": 0.0,
|
71 |
+
"mask_time_length": 10,
|
72 |
+
"mask_time_min_masks": 2,
|
73 |
+
"mask_time_min_space": 1,
|
74 |
+
"mask_time_other": 0.0,
|
75 |
+
"mask_time_prob": 0.05,
|
76 |
+
"mask_time_selection": "static",
|
77 |
+
"model_type": "wav2vec2",
|
78 |
+
"no_mask_channel_overlap": false,
|
79 |
+
"no_mask_time_overlap": false,
|
80 |
+
"num_adapter_layers": 3,
|
81 |
+
"num_attention_heads": 12,
|
82 |
+
"num_codevector_groups": 2,
|
83 |
+
"num_codevectors_per_group": 320,
|
84 |
+
"num_conv_pos_embedding_groups": 16,
|
85 |
+
"num_conv_pos_embeddings": 128,
|
86 |
+
"num_feat_extract_layers": 7,
|
87 |
+
"num_hidden_layers": 12,
|
88 |
+
"num_negatives": 100,
|
89 |
+
"output_hidden_size": 768,
|
90 |
+
"pad_token_id": 0,
|
91 |
+
"proj_codevector_dim": 256,
|
92 |
+
"tdnn_dilation": [
|
93 |
+
1,
|
94 |
+
2,
|
95 |
+
3,
|
96 |
+
1,
|
97 |
+
1
|
98 |
+
],
|
99 |
+
"tdnn_dim": [
|
100 |
+
512,
|
101 |
+
512,
|
102 |
+
512,
|
103 |
+
512,
|
104 |
+
1500
|
105 |
+
],
|
106 |
+
"tdnn_kernel": [
|
107 |
+
5,
|
108 |
+
3,
|
109 |
+
3,
|
110 |
+
1,
|
111 |
+
1
|
112 |
+
],
|
113 |
+
"torch_dtype": "float32",
|
114 |
+
"transformers_version": "4.36.0",
|
115 |
+
"use_weighted_layer_sum": false,
|
116 |
+
"vocab_size": 32,
|
117 |
+
"xvector_output_dim": 512
|
118 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2da18dce3298ed37d03b45fa4bef3e61e8bd9ea66818ab775d422891e4a821e
|
3 |
+
size 377611120
|
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 |
+
}
|
runs/Dec12_04-21-48_fe35c24a6b04/events.out.tfevents.1702354914.fe35c24a6b04.4020.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffa8278b2166d1b12dec6f8d20d52a2cfe6f2a0e45eaff4b97254e89bd1f03f8
|
3 |
+
size 6084
|
runs/Dec12_04-39-47_fe35c24a6b04/events.out.tfevents.1702355989.fe35c24a6b04.4020.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64a7bced3faed5a2df5e4b65f3b9d06a03e0774f689460be917bff7b3da7cbec
|
3 |
+
size 6080
|
runs/Dec12_04-43-19_fe35c24a6b04/events.out.tfevents.1702356201.fe35c24a6b04.4020.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5d54e4fb60f242f2bfd1390fb70a8aa4c2521bebd16898bb58e3ab07ad9124c
|
3 |
+
size 6080
|
runs/Dec12_04-44-22_fe35c24a6b04/events.out.tfevents.1702356263.fe35c24a6b04.4020.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35cc6cf2c8f24fd4d80833933e4b4ee58c13c884a1ff17cda044cf09eae9a3c9
|
3 |
+
size 6080
|
runs/Dec12_04-45-17_fe35c24a6b04/events.out.tfevents.1702356318.fe35c24a6b04.4020.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc6a08eeed683f26e8a9baa4c9f677530908dade21c7003ef85c8c9fcb14ff5f
|
3 |
+
size 6080
|
runs/Dec12_04-51-48_fe35c24a6b04/events.out.tfevents.1702356709.fe35c24a6b04.4020.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:465e16140bd821e77632da30c1b8a0892302fec34bc3b8c5d7faf6acea600486
|
3 |
+
size 6080
|
runs/Dec12_04-58-27_fe35c24a6b04/events.out.tfevents.1702357111.fe35c24a6b04.4020.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbb08305eb5b545749dd88e40ae5ec052fdc08ff94aaa089866b8504553a03dc
|
3 |
+
size 6080
|
runs/Dec12_04-59-52_fe35c24a6b04/events.out.tfevents.1702357201.fe35c24a6b04.4020.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1644f9ad87bc5c132adbe91cade7073ab724c1a75f264f4e6ad2ed15f98bd1ea
|
3 |
+
size 6080
|
runs/Dec12_05-06-53_fe35c24a6b04/events.out.tfevents.1702357617.fe35c24a6b04.4020.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da53342335a76eaa74fed5bf3cfcedf4b13c617020b2280f8a85ef2f8ccd78e9
|
3 |
+
size 6080
|
runs/Dec12_05-13-06_fe35c24a6b04/events.out.tfevents.1702357991.fe35c24a6b04.4020.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9a246220dbb8d24d49a0a36edaab57120e881b76c9445ce6b35ba6c54333688
|
3 |
+
size 6080
|
runs/Dec12_05-28-37_fe35c24a6b04/events.out.tfevents.1702358922.fe35c24a6b04.22147.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba7eca9f62c27387ce80fa4ddfdca3c2d266d41b5bcdd2ba5fc2938f99b025b3
|
3 |
+
size 6383
|
runs/Dec12_05-38-57_fe35c24a6b04/events.out.tfevents.1702359547.fe35c24a6b04.22147.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb348710b2069198a3c0a1a4c1b8650c1b14343b32796af1431a35f12cab6530
|
3 |
+
size 6073
|
runs/Dec12_05-42-45_fe35c24a6b04/events.out.tfevents.1702359774.fe35c24a6b04.22147.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8209b9460c178a1e38c7a3a7a11cf901d011e6695bb90cc6fbfe6bad002da39e
|
3 |
+
size 6385
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<pad>",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false,
|
9 |
+
"special": false
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": true,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": true,
|
16 |
+
"single_word": false,
|
17 |
+
"special": false
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": true,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": true,
|
24 |
+
"single_word": false,
|
25 |
+
"special": false
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": true,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": true,
|
32 |
+
"single_word": false,
|
33 |
+
"special": false
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"bos_token": "<s>",
|
37 |
+
"clean_up_tokenization_spaces": true,
|
38 |
+
"do_lower_case": false,
|
39 |
+
"do_normalize": true,
|
40 |
+
"eos_token": "</s>",
|
41 |
+
"model_max_length": 1000000000000000019884624838656,
|
42 |
+
"pad_token": "<pad>",
|
43 |
+
"processor_class": "Wav2Vec2Processor",
|
44 |
+
"replace_word_delimiter_char": " ",
|
45 |
+
"return_attention_mask": false,
|
46 |
+
"target_lang": null,
|
47 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
48 |
+
"unk_token": "<unk>",
|
49 |
+
"word_delimiter_token": "|"
|
50 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35c65ab2b364a62018d519cfadfd5c489412b751263469a5028199a481c4caaf
|
3 |
+
size 4728
|
vocab.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"'": 27,
|
3 |
+
"</s>": 2,
|
4 |
+
"<pad>": 0,
|
5 |
+
"<s>": 1,
|
6 |
+
"<unk>": 3,
|
7 |
+
"A": 7,
|
8 |
+
"B": 24,
|
9 |
+
"C": 19,
|
10 |
+
"D": 14,
|
11 |
+
"E": 5,
|
12 |
+
"F": 20,
|
13 |
+
"G": 21,
|
14 |
+
"H": 11,
|
15 |
+
"I": 10,
|
16 |
+
"J": 29,
|
17 |
+
"K": 26,
|
18 |
+
"L": 15,
|
19 |
+
"M": 17,
|
20 |
+
"N": 9,
|
21 |
+
"O": 8,
|
22 |
+
"P": 23,
|
23 |
+
"Q": 30,
|
24 |
+
"R": 13,
|
25 |
+
"S": 12,
|
26 |
+
"T": 6,
|
27 |
+
"U": 16,
|
28 |
+
"V": 25,
|
29 |
+
"W": 18,
|
30 |
+
"X": 28,
|
31 |
+
"Y": 22,
|
32 |
+
"Z": 31,
|
33 |
+
"|": 4
|
34 |
+
}
|