cristinakuo
commited on
Commit
•
9da1272
1
Parent(s):
601b44e
Training in progress, step 100
Browse files- config.json +31 -2
- 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/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +32 -0
- last-checkpoint/training_args.bin +3 -0
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,6 +1,9 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "facebook/wav2vec2-base",
|
3 |
"activation_dropout": 0.0,
|
|
|
|
|
|
|
4 |
"apply_spec_augment": true,
|
5 |
"architectures": [
|
6 |
"Wav2Vec2ForCTC"
|
@@ -62,8 +65,10 @@
|
|
62 |
"mask_channel_prob": 0.0,
|
63 |
"mask_channel_selection": "static",
|
64 |
"mask_feature_length": 10,
|
|
|
65 |
"mask_feature_prob": 0.0,
|
66 |
"mask_time_length": 10,
|
|
|
67 |
"mask_time_min_space": 1,
|
68 |
"mask_time_other": 0.0,
|
69 |
"mask_time_prob": 0.05,
|
@@ -71,6 +76,7 @@
|
|
71 |
"model_type": "wav2vec2",
|
72 |
"no_mask_channel_overlap": false,
|
73 |
"no_mask_time_overlap": false,
|
|
|
74 |
"num_attention_heads": 12,
|
75 |
"num_codevector_groups": 2,
|
76 |
"num_codevectors_per_group": 320,
|
@@ -79,10 +85,33 @@
|
|
79 |
"num_feat_extract_layers": 7,
|
80 |
"num_hidden_layers": 12,
|
81 |
"num_negatives": 100,
|
|
|
82 |
"pad_token_id": 26,
|
83 |
"proj_codevector_dim": 256,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
"torch_dtype": "float32",
|
85 |
"transformers_version": "4.11.3",
|
86 |
"use_weighted_layer_sum": false,
|
87 |
-
"vocab_size": 32
|
|
|
88 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base-es-voxpopuli-v2",
|
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"
|
|
|
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,
|
|
|
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,
|
|
|
85 |
"num_feat_extract_layers": 7,
|
86 |
"num_hidden_layers": 12,
|
87 |
"num_negatives": 100,
|
88 |
+
"output_hidden_size": 768,
|
89 |
"pad_token_id": 26,
|
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": "4.11.3",
|
114 |
"use_weighted_layer_sum": false,
|
115 |
+
"vocab_size": 32,
|
116 |
+
"xvector_output_dim": 512
|
117 |
}
|
last-checkpoint/config.json
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base-es-voxpopuli-v2",
|
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": 26,
|
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": "4.11.3",
|
114 |
+
"use_weighted_layer_sum": false,
|
115 |
+
"vocab_size": 32,
|
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 sha256:46dccdc4b2da5765df7738cf57f2db6b45f84a55ab8d903cb52c2fc90aef5e71
|
3 |
+
size 755293933
|
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 sha256:11f3756c024e1bce9c2bb91ab2ed378e9ab623ee7c9a5ac65e0c0ea11d156920
|
3 |
+
size 377670039
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd4342f3257715e3eb0aeec6580708012a375fec53662417e74134c3a7e19ac0
|
3 |
+
size 14567
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:701c13dd7bb9f56b7dd3aab7760cbe3da2db9a27c901ad10b8a23f3fd6d98db8
|
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": 1.36986301369863,
|
5 |
+
"global_step": 100,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.37,
|
12 |
+
"learning_rate": 1e-05,
|
13 |
+
"loss": 7.7643,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.37,
|
18 |
+
"eval_cer": 1.0,
|
19 |
+
"eval_loss": 3.6895599365234375,
|
20 |
+
"eval_runtime": 47.6167,
|
21 |
+
"eval_samples_per_second": 10.354,
|
22 |
+
"eval_steps_per_second": 1.302,
|
23 |
+
"eval_wer": 1.0,
|
24 |
+
"step": 100
|
25 |
+
}
|
26 |
+
],
|
27 |
+
"max_steps": 4380,
|
28 |
+
"num_train_epochs": 60,
|
29 |
+
"total_flos": 2.638076435083008e+16,
|
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 sha256:8fcc82192ef0a42a969b35b4e49870954fceac78ffdafa4fc1d103b74b8f6678
|
3 |
+
size 2863
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377670039
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11f3756c024e1bce9c2bb91ab2ed378e9ab623ee7c9a5ac65e0c0ea11d156920
|
3 |
size 377670039
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2863
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fcc82192ef0a42a969b35b4e49870954fceac78ffdafa4fc1d103b74b8f6678
|
3 |
size 2863
|