Training in progress, step 200
Browse files- config.json +12 -19
- preprocessor_config.json +2 -2
- pytorch_model.bin +2 -2
- runs/Jun19_16-01-57_bf13bc1f00ad/events.out.tfevents.1687190549.bf13bc1f00ad.26489.0 +3 -0
- runs/Jun19_16-03-41_bf13bc1f00ad/events.out.tfevents.1687190646.bf13bc1f00ad.26972.0 +3 -0
- special_tokens_map.json +42 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_attn_dim": null,
|
5 |
"adapter_kernel_size": 3,
|
@@ -12,9 +12,9 @@
|
|
12 |
"attention_dropout": 0.0,
|
13 |
"bos_token_id": 1,
|
14 |
"classifier_proj_size": 256,
|
15 |
-
"codevector_dim":
|
16 |
"contrastive_logits_temperature": 0.1,
|
17 |
-
"conv_bias":
|
18 |
"conv_dim": [
|
19 |
512,
|
20 |
512,
|
@@ -45,48 +45,41 @@
|
|
45 |
"ctc_loss_reduction": "mean",
|
46 |
"ctc_zero_infinity": false,
|
47 |
"diversity_loss_weight": 0.1,
|
48 |
-
"do_stable_layer_norm":
|
49 |
"eos_token_id": 2,
|
50 |
"feat_extract_activation": "gelu",
|
51 |
"feat_extract_dropout": 0.0,
|
52 |
-
"feat_extract_norm": "
|
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 |
-
"
|
|
|
59 |
"initializer_range": 0.02,
|
60 |
-
"intermediate_size":
|
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 |
"num_adapter_layers": 3,
|
79 |
-
"num_attention_heads":
|
80 |
"num_codevector_groups": 2,
|
81 |
"num_codevectors_per_group": 320,
|
82 |
"num_conv_pos_embedding_groups": 16,
|
83 |
"num_conv_pos_embeddings": 128,
|
84 |
"num_feat_extract_layers": 7,
|
85 |
-
"num_hidden_layers":
|
86 |
"num_negatives": 100,
|
87 |
-
"output_hidden_size":
|
88 |
"pad_token_id": 94,
|
89 |
-
"proj_codevector_dim":
|
90 |
"tdnn_dilation": [
|
91 |
1,
|
92 |
2,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "nguyenvulebinh/wav2vec2-base-vietnamese-250h",
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_attn_dim": null,
|
5 |
"adapter_kernel_size": 3,
|
|
|
12 |
"attention_dropout": 0.0,
|
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,
|
|
|
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_dropout": 0.0,
|
52 |
+
"feat_extract_norm": "group",
|
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_dropout_prob": 0.1,
|
59 |
+
"hidden_size": 768,
|
60 |
"initializer_range": 0.02,
|
61 |
+
"intermediate_size": 3072,
|
62 |
"layer_norm_eps": 1e-05,
|
63 |
"layerdrop": 0.0,
|
|
|
|
|
|
|
|
|
|
|
64 |
"mask_feature_length": 10,
|
65 |
"mask_feature_min_masks": 0,
|
66 |
"mask_feature_prob": 0.0,
|
67 |
"mask_time_length": 10,
|
68 |
"mask_time_min_masks": 2,
|
|
|
|
|
69 |
"mask_time_prob": 0.05,
|
|
|
70 |
"model_type": "wav2vec2",
|
71 |
"num_adapter_layers": 3,
|
72 |
+
"num_attention_heads": 12,
|
73 |
"num_codevector_groups": 2,
|
74 |
"num_codevectors_per_group": 320,
|
75 |
"num_conv_pos_embedding_groups": 16,
|
76 |
"num_conv_pos_embeddings": 128,
|
77 |
"num_feat_extract_layers": 7,
|
78 |
+
"num_hidden_layers": 12,
|
79 |
"num_negatives": 100,
|
80 |
+
"output_hidden_size": 768,
|
81 |
"pad_token_id": 94,
|
82 |
+
"proj_codevector_dim": 256,
|
83 |
"tdnn_dilation": [
|
84 |
1,
|
85 |
2,
|
preprocessor_config.json
CHANGED
@@ -3,8 +3,8 @@
|
|
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":
|
9 |
"sampling_rate": 16000
|
10 |
}
|
|
|
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
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:096900482c468ad643e75a69d27f33144e4e137b80ec17817dee04d675c016fa
|
3 |
+
size 377858721
|
runs/Jun19_16-01-57_bf13bc1f00ad/events.out.tfevents.1687190549.bf13bc1f00ad.26489.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9cfee422623ee085e30e2afe1d3829a5f58640b60625d311eba44863a4b2b73
|
3 |
+
size 5878
|
runs/Jun19_16-03-41_bf13bc1f00ad/events.out.tfevents.1687190646.bf13bc1f00ad.26972.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14331d12b4ad500e388e8450d385043707bdbe83c6c9dc2d409a940880f6c44c
|
3 |
+
size 6196
|
special_tokens_map.json
CHANGED
@@ -63,6 +63,48 @@
|
|
63 |
"rstrip": false,
|
64 |
"single_word": false
|
65 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
{
|
67 |
"content": "</s>",
|
68 |
"lstrip": false,
|
|
|
63 |
"rstrip": false,
|
64 |
"single_word": false
|
65 |
},
|
66 |
+
{
|
67 |
+
"content": "</s>",
|
68 |
+
"lstrip": false,
|
69 |
+
"normalized": true,
|
70 |
+
"rstrip": false,
|
71 |
+
"single_word": false
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"content": "<s>",
|
75 |
+
"lstrip": false,
|
76 |
+
"normalized": true,
|
77 |
+
"rstrip": false,
|
78 |
+
"single_word": false
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"content": "</s>",
|
82 |
+
"lstrip": false,
|
83 |
+
"normalized": true,
|
84 |
+
"rstrip": false,
|
85 |
+
"single_word": false
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"content": "<s>",
|
89 |
+
"lstrip": false,
|
90 |
+
"normalized": true,
|
91 |
+
"rstrip": false,
|
92 |
+
"single_word": false
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"content": "</s>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"content": "<s>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": true,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false
|
107 |
+
},
|
108 |
{
|
109 |
"content": "</s>",
|
110 |
"lstrip": false,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3963
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08ea747381fbe56ba289e7b44b4efb4717817b7490289709924a87e4f427f096
|
3 |
size 3963
|