Training in progress, epoch 1
Browse files
config.json
CHANGED
@@ -1,20 +1,14 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "facebook/
|
3 |
"activation_dropout": 0.1,
|
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 |
-
"
|
11 |
],
|
12 |
"attention_dropout": 0.1,
|
13 |
"bos_token_id": 1,
|
14 |
"classifier_proj_size": 256,
|
15 |
-
"
|
16 |
-
"contrastive_logits_temperature": 0.1,
|
17 |
-
"conv_bias": false,
|
18 |
"conv_dim": [
|
19 |
512,
|
20 |
512,
|
@@ -45,19 +39,19 @@
|
|
45 |
"ctc_loss_reduction": "sum",
|
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": 0.1,
|
54 |
-
"
|
55 |
"final_dropout": 0.1,
|
56 |
"gradient_checkpointing": false,
|
57 |
"hidden_act": "gelu",
|
58 |
"hidden_dropout": 0.1,
|
59 |
"hidden_dropout_prob": 0.1,
|
60 |
-
"hidden_size":
|
61 |
"id2label": {
|
62 |
"0": "artifact",
|
63 |
"1": "extrahls",
|
@@ -66,7 +60,7 @@
|
|
66 |
"4": "normal"
|
67 |
},
|
68 |
"initializer_range": 0.02,
|
69 |
-
"intermediate_size":
|
70 |
"label2id": {
|
71 |
"artifact": "0",
|
72 |
"extrahls": "1",
|
@@ -82,43 +76,15 @@
|
|
82 |
"mask_time_length": 10,
|
83 |
"mask_time_min_masks": 2,
|
84 |
"mask_time_prob": 0.05,
|
85 |
-
"model_type": "
|
86 |
-
"
|
87 |
-
"num_attention_heads": 12,
|
88 |
-
"num_codevector_groups": 2,
|
89 |
-
"num_codevectors_per_group": 320,
|
90 |
"num_conv_pos_embedding_groups": 16,
|
91 |
"num_conv_pos_embeddings": 128,
|
92 |
"num_feat_extract_layers": 7,
|
93 |
-
"num_hidden_layers":
|
94 |
-
"num_negatives": 100,
|
95 |
-
"output_hidden_size": 768,
|
96 |
"pad_token_id": 0,
|
97 |
-
"proj_codevector_dim": 256,
|
98 |
-
"tdnn_dilation": [
|
99 |
-
1,
|
100 |
-
2,
|
101 |
-
3,
|
102 |
-
1,
|
103 |
-
1
|
104 |
-
],
|
105 |
-
"tdnn_dim": [
|
106 |
-
512,
|
107 |
-
512,
|
108 |
-
512,
|
109 |
-
512,
|
110 |
-
1500
|
111 |
-
],
|
112 |
-
"tdnn_kernel": [
|
113 |
-
5,
|
114 |
-
3,
|
115 |
-
3,
|
116 |
-
1,
|
117 |
-
1
|
118 |
-
],
|
119 |
"torch_dtype": "float32",
|
120 |
"transformers_version": "4.39.3",
|
121 |
"use_weighted_layer_sum": false,
|
122 |
-
"vocab_size": 32
|
123 |
-
"xvector_output_dim": 512
|
124 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/hubert-large-ls960-ft",
|
3 |
"activation_dropout": 0.1,
|
|
|
|
|
|
|
|
|
4 |
"apply_spec_augment": true,
|
5 |
"architectures": [
|
6 |
+
"HubertForSequenceClassification"
|
7 |
],
|
8 |
"attention_dropout": 0.1,
|
9 |
"bos_token_id": 1,
|
10 |
"classifier_proj_size": 256,
|
11 |
+
"conv_bias": true,
|
|
|
|
|
12 |
"conv_dim": [
|
13 |
512,
|
14 |
512,
|
|
|
39 |
"ctc_loss_reduction": "sum",
|
40 |
"ctc_zero_infinity": false,
|
41 |
"diversity_loss_weight": 0.1,
|
42 |
+
"do_stable_layer_norm": true,
|
43 |
"eos_token_id": 2,
|
44 |
"feat_extract_activation": "gelu",
|
45 |
"feat_extract_dropout": 0.0,
|
46 |
+
"feat_extract_norm": "layer",
|
47 |
"feat_proj_dropout": 0.1,
|
48 |
+
"feat_proj_layer_norm": true,
|
49 |
"final_dropout": 0.1,
|
50 |
"gradient_checkpointing": false,
|
51 |
"hidden_act": "gelu",
|
52 |
"hidden_dropout": 0.1,
|
53 |
"hidden_dropout_prob": 0.1,
|
54 |
+
"hidden_size": 1024,
|
55 |
"id2label": {
|
56 |
"0": "artifact",
|
57 |
"1": "extrahls",
|
|
|
60 |
"4": "normal"
|
61 |
},
|
62 |
"initializer_range": 0.02,
|
63 |
+
"intermediate_size": 4096,
|
64 |
"label2id": {
|
65 |
"artifact": "0",
|
66 |
"extrahls": "1",
|
|
|
76 |
"mask_time_length": 10,
|
77 |
"mask_time_min_masks": 2,
|
78 |
"mask_time_prob": 0.05,
|
79 |
+
"model_type": "hubert",
|
80 |
+
"num_attention_heads": 16,
|
|
|
|
|
|
|
81 |
"num_conv_pos_embedding_groups": 16,
|
82 |
"num_conv_pos_embeddings": 128,
|
83 |
"num_feat_extract_layers": 7,
|
84 |
+
"num_hidden_layers": 24,
|
|
|
|
|
85 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
86 |
"torch_dtype": "float32",
|
87 |
"transformers_version": "4.39.3",
|
88 |
"use_weighted_layer_sum": false,
|
89 |
+
"vocab_size": 32
|
|
|
90 |
}
|
model.safetensors
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 sha256:87c40d7bd08044657533c893f10043efa6c90754d943cff4a91e2d8716f79e33
|
3 |
+
size 1262861548
|
preprocessor_config.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
-
"padding_value": 0
|
7 |
-
"return_attention_mask":
|
8 |
"sampling_rate": 16000
|
9 |
}
|
|
|
3 |
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
+
"padding_value": 0,
|
7 |
+
"return_attention_mask": true,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
runs/Apr04_09-04-13_c3596e20e628/events.out.tfevents.1712221454.c3596e20e628.396.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5db65044a53a8681f8189d392670c3a8b13fcea138188f53ad1d961f351f7327
|
3 |
+
size 6259
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d368c116d8b964d9fbf10ed9ae06ffbb8e026dac22eb05fb22a2a1ddae91011d
|
3 |
size 4920
|