Commit
•
0d6932b
1
Parent(s):
92a1fff
Training in progress, step 24900
Browse files- .gitignore +1 -0
- config.json +117 -0
- last-checkpoint/config.json +117 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/preprocessor_config.json +9 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scaler.pt +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +32 -0
- last-checkpoint/training_args.bin +3 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
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": 27,
|
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": "4.18.0",
|
114 |
+
"use_weighted_layer_sum": false,
|
115 |
+
"vocab_size": 28,
|
116 |
+
"xvector_output_dim": 512
|
117 |
+
}
|
last-checkpoint/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": 27,
|
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": "4.18.0",
|
114 |
+
"use_weighted_layer_sum": false,
|
115 |
+
"vocab_size": 28,
|
116 |
+
"xvector_output_dim": 512
|
117 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7b2b08bf0a80243324b6b918a0775c5194f10bcb1a8e9c412ebf36e89dbde1e
|
3 |
+
size 174303
|
last-checkpoint/preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"return_attention_mask": false,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e4e9c56c0366a8f5050b1a23df13d78519db2fca9ca46c06cc32b6f270f4813
|
3 |
+
size 377644503
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a66ab641e0ac57991319d4af3c7c77406de7c97ad64f52fa2ede00df820c6a3
|
3 |
+
size 14567
|
last-checkpoint/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:026a4e9c216b80f8a12dcf7d72fdbd180a598dd663ee6a84df16a4756f040865
|
3 |
+
size 559
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1a0410fd0ef586fb7fb2915f87208eb1b42ec67073ccb68b6658757368a7f68
|
3 |
+
size 623
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 50.0,
|
5 |
+
"global_step": 24900,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 50.0,
|
12 |
+
"learning_rate": 9.47419150285352e-05,
|
13 |
+
"loss": 14.1226,
|
14 |
+
"step": 24900
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 50.0,
|
18 |
+
"eval_cer": 0.9558441558441558,
|
19 |
+
"eval_loss": 3.0782525539398193,
|
20 |
+
"eval_runtime": 1.0533,
|
21 |
+
"eval_samples_per_second": 199.372,
|
22 |
+
"eval_steps_per_second": 25.634,
|
23 |
+
"eval_wer": 1.0,
|
24 |
+
"step": 24900
|
25 |
+
}
|
26 |
+
],
|
27 |
+
"max_steps": 249000,
|
28 |
+
"num_train_epochs": 500,
|
29 |
+
"total_flos": 2.3044539516961427e+19,
|
30 |
+
"trial_name": null,
|
31 |
+
"trial_params": null
|
32 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b69cf0e65fb688a91275e9f5dc1f22ef5bf55dbdf7551099013fd72ed472f3f8
|
3 |
+
size 3119
|
preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"return_attention_mask": false,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e4e9c56c0366a8f5050b1a23df13d78519db2fca9ca46c06cc32b6f270f4813
|
3 |
+
size 377644503
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b69cf0e65fb688a91275e9f5dc1f22ef5bf55dbdf7551099013fd72ed472f3f8
|
3 |
+
size 3119
|