Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-1390/config.json +125 -0
- checkpoint-1390/optimizer.pt +3 -0
- checkpoint-1390/preprocessor_config.json +9 -0
- checkpoint-1390/pytorch_model.bin +3 -0
- checkpoint-1390/rng_state.pth +3 -0
- checkpoint-1390/scheduler.pt +3 -0
- checkpoint-1390/trainer_state.json +0 -0
- checkpoint-1390/training_args.bin +3 -0
- checkpoint-2085/config.json +125 -0
- checkpoint-2085/optimizer.pt +3 -0
- checkpoint-2085/preprocessor_config.json +9 -0
- checkpoint-2085/pytorch_model.bin +3 -0
- checkpoint-2085/rng_state.pth +3 -0
- checkpoint-2085/scheduler.pt +3 -0
- checkpoint-2085/trainer_state.json +0 -0
- checkpoint-2085/training_args.bin +3 -0
- checkpoint-2780/config.json +125 -0
- checkpoint-2780/optimizer.pt +3 -0
- checkpoint-2780/preprocessor_config.json +9 -0
- checkpoint-2780/pytorch_model.bin +3 -0
- checkpoint-2780/rng_state.pth +3 -0
- checkpoint-2780/scheduler.pt +3 -0
- checkpoint-2780/trainer_state.json +0 -0
- checkpoint-2780/training_args.bin +3 -0
- checkpoint-3475/config.json +125 -0
- checkpoint-3475/optimizer.pt +3 -0
- checkpoint-3475/preprocessor_config.json +9 -0
- checkpoint-3475/pytorch_model.bin +3 -0
- checkpoint-3475/rng_state.pth +3 -0
- checkpoint-3475/scheduler.pt +3 -0
- checkpoint-3475/trainer_state.json +0 -0
- checkpoint-3475/training_args.bin +3 -0
- checkpoint-4170/config.json +125 -0
- checkpoint-4170/optimizer.pt +3 -0
- checkpoint-4170/preprocessor_config.json +9 -0
- checkpoint-4170/pytorch_model.bin +3 -0
- checkpoint-4170/rng_state.pth +3 -0
- checkpoint-4170/scheduler.pt +3 -0
- checkpoint-4170/trainer_state.json +0 -0
- checkpoint-4170/training_args.bin +3 -0
- checkpoint-4865/config.json +125 -0
- checkpoint-4865/optimizer.pt +3 -0
- checkpoint-4865/preprocessor_config.json +9 -0
- checkpoint-4865/pytorch_model.bin +3 -0
- checkpoint-4865/rng_state.pth +3 -0
- checkpoint-4865/scheduler.pt +3 -0
- checkpoint-4865/trainer_state.json +0 -0
- checkpoint-4865/training_args.bin +3 -0
- checkpoint-5560/config.json +125 -0
- checkpoint-5560/optimizer.pt +3 -0
checkpoint-1390/config.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base-960h",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"Wav2Vec2ForSequenceClassification"
|
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": "sum",
|
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_dropout": 0.0,
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.1,
|
55 |
+
"gradient_checkpointing": false,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_dropout_prob": 0.1,
|
59 |
+
"hidden_size": 768,
|
60 |
+
"id2label": {
|
61 |
+
"0": "english",
|
62 |
+
"1": "spanish",
|
63 |
+
"2": "arabic",
|
64 |
+
"3": "french",
|
65 |
+
"4": "mandarin",
|
66 |
+
"5": "other"
|
67 |
+
},
|
68 |
+
"initializer_range": 0.02,
|
69 |
+
"intermediate_size": 3072,
|
70 |
+
"label2id": {
|
71 |
+
"LABEL_0": 0,
|
72 |
+
"LABEL_1": 1,
|
73 |
+
"LABEL_2": 2,
|
74 |
+
"LABEL_3": 3,
|
75 |
+
"LABEL_4": 4,
|
76 |
+
"LABEL_5": 5
|
77 |
+
},
|
78 |
+
"layer_norm_eps": 1e-05,
|
79 |
+
"layerdrop": 0.1,
|
80 |
+
"mask_feature_length": 10,
|
81 |
+
"mask_feature_min_masks": 0,
|
82 |
+
"mask_feature_prob": 0.0,
|
83 |
+
"mask_time_length": 10,
|
84 |
+
"mask_time_min_masks": 2,
|
85 |
+
"mask_time_prob": 0.05,
|
86 |
+
"model_type": "wav2vec2",
|
87 |
+
"num_adapter_layers": 3,
|
88 |
+
"num_attention_heads": 12,
|
89 |
+
"num_codevector_groups": 2,
|
90 |
+
"num_codevectors_per_group": 320,
|
91 |
+
"num_conv_pos_embedding_groups": 16,
|
92 |
+
"num_conv_pos_embeddings": 128,
|
93 |
+
"num_feat_extract_layers": 7,
|
94 |
+
"num_hidden_layers": 12,
|
95 |
+
"num_negatives": 100,
|
96 |
+
"output_hidden_size": 768,
|
97 |
+
"pad_token_id": 0,
|
98 |
+
"proj_codevector_dim": 256,
|
99 |
+
"tdnn_dilation": [
|
100 |
+
1,
|
101 |
+
2,
|
102 |
+
3,
|
103 |
+
1,
|
104 |
+
1
|
105 |
+
],
|
106 |
+
"tdnn_dim": [
|
107 |
+
512,
|
108 |
+
512,
|
109 |
+
512,
|
110 |
+
512,
|
111 |
+
1500
|
112 |
+
],
|
113 |
+
"tdnn_kernel": [
|
114 |
+
5,
|
115 |
+
3,
|
116 |
+
3,
|
117 |
+
1,
|
118 |
+
1
|
119 |
+
],
|
120 |
+
"torch_dtype": "float32",
|
121 |
+
"transformers_version": "4.28.1",
|
122 |
+
"use_weighted_layer_sum": false,
|
123 |
+
"vocab_size": 32,
|
124 |
+
"xvector_output_dim": 512
|
125 |
+
}
|
checkpoint-1390/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9dba9a3d3689ab22fb66cb27fda7bd6656a3e069ce7512547e79f6521b703cf5
|
3 |
+
size 756685669
|
checkpoint-1390/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 |
+
}
|
checkpoint-1390/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57d870c46842a1cbc97d5bce9d68d29fc86f7f8b01465600ee651d0544c5134e
|
3 |
+
size 378352659
|
checkpoint-1390/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09ab720adb20af6df73c6afad40f8d19762c9f925417561f368ec0b44f220c4f
|
3 |
+
size 14567
|
checkpoint-1390/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15bc70771c8dc62fe6199258c446b2652a15dafb01a698f8ea5f4b69ac58e26e
|
3 |
+
size 623
|
checkpoint-1390/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1390/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e586ffec83af94e0cf9ea31750e6c3ca1bf1ee016bdd398b7fe339f74b71c58
|
3 |
+
size 3567
|
checkpoint-2085/config.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base-960h",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"Wav2Vec2ForSequenceClassification"
|
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": "sum",
|
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_dropout": 0.0,
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.1,
|
55 |
+
"gradient_checkpointing": false,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_dropout_prob": 0.1,
|
59 |
+
"hidden_size": 768,
|
60 |
+
"id2label": {
|
61 |
+
"0": "english",
|
62 |
+
"1": "spanish",
|
63 |
+
"2": "arabic",
|
64 |
+
"3": "french",
|
65 |
+
"4": "mandarin",
|
66 |
+
"5": "other"
|
67 |
+
},
|
68 |
+
"initializer_range": 0.02,
|
69 |
+
"intermediate_size": 3072,
|
70 |
+
"label2id": {
|
71 |
+
"LABEL_0": 0,
|
72 |
+
"LABEL_1": 1,
|
73 |
+
"LABEL_2": 2,
|
74 |
+
"LABEL_3": 3,
|
75 |
+
"LABEL_4": 4,
|
76 |
+
"LABEL_5": 5
|
77 |
+
},
|
78 |
+
"layer_norm_eps": 1e-05,
|
79 |
+
"layerdrop": 0.1,
|
80 |
+
"mask_feature_length": 10,
|
81 |
+
"mask_feature_min_masks": 0,
|
82 |
+
"mask_feature_prob": 0.0,
|
83 |
+
"mask_time_length": 10,
|
84 |
+
"mask_time_min_masks": 2,
|
85 |
+
"mask_time_prob": 0.05,
|
86 |
+
"model_type": "wav2vec2",
|
87 |
+
"num_adapter_layers": 3,
|
88 |
+
"num_attention_heads": 12,
|
89 |
+
"num_codevector_groups": 2,
|
90 |
+
"num_codevectors_per_group": 320,
|
91 |
+
"num_conv_pos_embedding_groups": 16,
|
92 |
+
"num_conv_pos_embeddings": 128,
|
93 |
+
"num_feat_extract_layers": 7,
|
94 |
+
"num_hidden_layers": 12,
|
95 |
+
"num_negatives": 100,
|
96 |
+
"output_hidden_size": 768,
|
97 |
+
"pad_token_id": 0,
|
98 |
+
"proj_codevector_dim": 256,
|
99 |
+
"tdnn_dilation": [
|
100 |
+
1,
|
101 |
+
2,
|
102 |
+
3,
|
103 |
+
1,
|
104 |
+
1
|
105 |
+
],
|
106 |
+
"tdnn_dim": [
|
107 |
+
512,
|
108 |
+
512,
|
109 |
+
512,
|
110 |
+
512,
|
111 |
+
1500
|
112 |
+
],
|
113 |
+
"tdnn_kernel": [
|
114 |
+
5,
|
115 |
+
3,
|
116 |
+
3,
|
117 |
+
1,
|
118 |
+
1
|
119 |
+
],
|
120 |
+
"torch_dtype": "float32",
|
121 |
+
"transformers_version": "4.28.1",
|
122 |
+
"use_weighted_layer_sum": false,
|
123 |
+
"vocab_size": 32,
|
124 |
+
"xvector_output_dim": 512
|
125 |
+
}
|
checkpoint-2085/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c439813f3f829ce34679e8b80afc75be5fbafacb7619d3e6434edc77b10d880
|
3 |
+
size 756685669
|
checkpoint-2085/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 |
+
}
|
checkpoint-2085/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:773dfcd5d87c0bb990f9e976e3754e7e15a3fef82d4f8e1a038de1c1154fc26c
|
3 |
+
size 378352659
|
checkpoint-2085/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:701e95ed7267123ba519a0235a69162f64ce36e9a452f51a9e0222bab0ca3a36
|
3 |
+
size 14567
|
checkpoint-2085/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27938b4a7ab63b8a6f6318a2da4f4938012468ddd2c83dbf284d9ff66e9f3656
|
3 |
+
size 623
|
checkpoint-2085/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2085/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e586ffec83af94e0cf9ea31750e6c3ca1bf1ee016bdd398b7fe339f74b71c58
|
3 |
+
size 3567
|
checkpoint-2780/config.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base-960h",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"Wav2Vec2ForSequenceClassification"
|
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": "sum",
|
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_dropout": 0.0,
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.1,
|
55 |
+
"gradient_checkpointing": false,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_dropout_prob": 0.1,
|
59 |
+
"hidden_size": 768,
|
60 |
+
"id2label": {
|
61 |
+
"0": "english",
|
62 |
+
"1": "spanish",
|
63 |
+
"2": "arabic",
|
64 |
+
"3": "french",
|
65 |
+
"4": "mandarin",
|
66 |
+
"5": "other"
|
67 |
+
},
|
68 |
+
"initializer_range": 0.02,
|
69 |
+
"intermediate_size": 3072,
|
70 |
+
"label2id": {
|
71 |
+
"LABEL_0": 0,
|
72 |
+
"LABEL_1": 1,
|
73 |
+
"LABEL_2": 2,
|
74 |
+
"LABEL_3": 3,
|
75 |
+
"LABEL_4": 4,
|
76 |
+
"LABEL_5": 5
|
77 |
+
},
|
78 |
+
"layer_norm_eps": 1e-05,
|
79 |
+
"layerdrop": 0.1,
|
80 |
+
"mask_feature_length": 10,
|
81 |
+
"mask_feature_min_masks": 0,
|
82 |
+
"mask_feature_prob": 0.0,
|
83 |
+
"mask_time_length": 10,
|
84 |
+
"mask_time_min_masks": 2,
|
85 |
+
"mask_time_prob": 0.05,
|
86 |
+
"model_type": "wav2vec2",
|
87 |
+
"num_adapter_layers": 3,
|
88 |
+
"num_attention_heads": 12,
|
89 |
+
"num_codevector_groups": 2,
|
90 |
+
"num_codevectors_per_group": 320,
|
91 |
+
"num_conv_pos_embedding_groups": 16,
|
92 |
+
"num_conv_pos_embeddings": 128,
|
93 |
+
"num_feat_extract_layers": 7,
|
94 |
+
"num_hidden_layers": 12,
|
95 |
+
"num_negatives": 100,
|
96 |
+
"output_hidden_size": 768,
|
97 |
+
"pad_token_id": 0,
|
98 |
+
"proj_codevector_dim": 256,
|
99 |
+
"tdnn_dilation": [
|
100 |
+
1,
|
101 |
+
2,
|
102 |
+
3,
|
103 |
+
1,
|
104 |
+
1
|
105 |
+
],
|
106 |
+
"tdnn_dim": [
|
107 |
+
512,
|
108 |
+
512,
|
109 |
+
512,
|
110 |
+
512,
|
111 |
+
1500
|
112 |
+
],
|
113 |
+
"tdnn_kernel": [
|
114 |
+
5,
|
115 |
+
3,
|
116 |
+
3,
|
117 |
+
1,
|
118 |
+
1
|
119 |
+
],
|
120 |
+
"torch_dtype": "float32",
|
121 |
+
"transformers_version": "4.28.1",
|
122 |
+
"use_weighted_layer_sum": false,
|
123 |
+
"vocab_size": 32,
|
124 |
+
"xvector_output_dim": 512
|
125 |
+
}
|
checkpoint-2780/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:834d71f1927fa5e3997bea7dd8375f5d90954ef60974e1b71971f0e4de519cba
|
3 |
+
size 756685669
|
checkpoint-2780/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 |
+
}
|
checkpoint-2780/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42b9e3df5a58141c976f6649a4c0a15f4c67bb014e6a5f9579bd8b60eb595140
|
3 |
+
size 378352659
|
checkpoint-2780/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5ea650b347b3b6ecee258fce29bf4b71f686495c8bbfbe370bff3d34a90df47
|
3 |
+
size 14567
|
checkpoint-2780/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da316c642ce53edc59b929694aa5cda251eee014f335feae6e39c42a93216c61
|
3 |
+
size 623
|
checkpoint-2780/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2780/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e586ffec83af94e0cf9ea31750e6c3ca1bf1ee016bdd398b7fe339f74b71c58
|
3 |
+
size 3567
|
checkpoint-3475/config.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base-960h",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"Wav2Vec2ForSequenceClassification"
|
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": "sum",
|
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_dropout": 0.0,
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.1,
|
55 |
+
"gradient_checkpointing": false,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_dropout_prob": 0.1,
|
59 |
+
"hidden_size": 768,
|
60 |
+
"id2label": {
|
61 |
+
"0": "english",
|
62 |
+
"1": "spanish",
|
63 |
+
"2": "arabic",
|
64 |
+
"3": "french",
|
65 |
+
"4": "mandarin",
|
66 |
+
"5": "other"
|
67 |
+
},
|
68 |
+
"initializer_range": 0.02,
|
69 |
+
"intermediate_size": 3072,
|
70 |
+
"label2id": {
|
71 |
+
"LABEL_0": 0,
|
72 |
+
"LABEL_1": 1,
|
73 |
+
"LABEL_2": 2,
|
74 |
+
"LABEL_3": 3,
|
75 |
+
"LABEL_4": 4,
|
76 |
+
"LABEL_5": 5
|
77 |
+
},
|
78 |
+
"layer_norm_eps": 1e-05,
|
79 |
+
"layerdrop": 0.1,
|
80 |
+
"mask_feature_length": 10,
|
81 |
+
"mask_feature_min_masks": 0,
|
82 |
+
"mask_feature_prob": 0.0,
|
83 |
+
"mask_time_length": 10,
|
84 |
+
"mask_time_min_masks": 2,
|
85 |
+
"mask_time_prob": 0.05,
|
86 |
+
"model_type": "wav2vec2",
|
87 |
+
"num_adapter_layers": 3,
|
88 |
+
"num_attention_heads": 12,
|
89 |
+
"num_codevector_groups": 2,
|
90 |
+
"num_codevectors_per_group": 320,
|
91 |
+
"num_conv_pos_embedding_groups": 16,
|
92 |
+
"num_conv_pos_embeddings": 128,
|
93 |
+
"num_feat_extract_layers": 7,
|
94 |
+
"num_hidden_layers": 12,
|
95 |
+
"num_negatives": 100,
|
96 |
+
"output_hidden_size": 768,
|
97 |
+
"pad_token_id": 0,
|
98 |
+
"proj_codevector_dim": 256,
|
99 |
+
"tdnn_dilation": [
|
100 |
+
1,
|
101 |
+
2,
|
102 |
+
3,
|
103 |
+
1,
|
104 |
+
1
|
105 |
+
],
|
106 |
+
"tdnn_dim": [
|
107 |
+
512,
|
108 |
+
512,
|
109 |
+
512,
|
110 |
+
512,
|
111 |
+
1500
|
112 |
+
],
|
113 |
+
"tdnn_kernel": [
|
114 |
+
5,
|
115 |
+
3,
|
116 |
+
3,
|
117 |
+
1,
|
118 |
+
1
|
119 |
+
],
|
120 |
+
"torch_dtype": "float32",
|
121 |
+
"transformers_version": "4.28.1",
|
122 |
+
"use_weighted_layer_sum": false,
|
123 |
+
"vocab_size": 32,
|
124 |
+
"xvector_output_dim": 512
|
125 |
+
}
|
checkpoint-3475/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e41dcf11f5839069ac03206b2628aac37c4b5c78dd7bb51c0c340ffa8ae127ed
|
3 |
+
size 756685669
|
checkpoint-3475/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 |
+
}
|
checkpoint-3475/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2edc7253191c15c6bd80f1bf64ee31f8174bc4d0d1628b2c71a80a8ac40d3274
|
3 |
+
size 378352659
|
checkpoint-3475/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f10ee3c3a9763cedee0844ccf45e7435ab6fc9ed45f9c5ce0200510d7e18dc7a
|
3 |
+
size 14567
|
checkpoint-3475/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c884f70eb9e23c04598e0a4a050d6cd3b01180465a73986f2ce2877a449212a
|
3 |
+
size 623
|
checkpoint-3475/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3475/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e586ffec83af94e0cf9ea31750e6c3ca1bf1ee016bdd398b7fe339f74b71c58
|
3 |
+
size 3567
|
checkpoint-4170/config.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base-960h",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"Wav2Vec2ForSequenceClassification"
|
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": "sum",
|
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_dropout": 0.0,
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.1,
|
55 |
+
"gradient_checkpointing": false,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_dropout_prob": 0.1,
|
59 |
+
"hidden_size": 768,
|
60 |
+
"id2label": {
|
61 |
+
"0": "english",
|
62 |
+
"1": "spanish",
|
63 |
+
"2": "arabic",
|
64 |
+
"3": "french",
|
65 |
+
"4": "mandarin",
|
66 |
+
"5": "other"
|
67 |
+
},
|
68 |
+
"initializer_range": 0.02,
|
69 |
+
"intermediate_size": 3072,
|
70 |
+
"label2id": {
|
71 |
+
"LABEL_0": 0,
|
72 |
+
"LABEL_1": 1,
|
73 |
+
"LABEL_2": 2,
|
74 |
+
"LABEL_3": 3,
|
75 |
+
"LABEL_4": 4,
|
76 |
+
"LABEL_5": 5
|
77 |
+
},
|
78 |
+
"layer_norm_eps": 1e-05,
|
79 |
+
"layerdrop": 0.1,
|
80 |
+
"mask_feature_length": 10,
|
81 |
+
"mask_feature_min_masks": 0,
|
82 |
+
"mask_feature_prob": 0.0,
|
83 |
+
"mask_time_length": 10,
|
84 |
+
"mask_time_min_masks": 2,
|
85 |
+
"mask_time_prob": 0.05,
|
86 |
+
"model_type": "wav2vec2",
|
87 |
+
"num_adapter_layers": 3,
|
88 |
+
"num_attention_heads": 12,
|
89 |
+
"num_codevector_groups": 2,
|
90 |
+
"num_codevectors_per_group": 320,
|
91 |
+
"num_conv_pos_embedding_groups": 16,
|
92 |
+
"num_conv_pos_embeddings": 128,
|
93 |
+
"num_feat_extract_layers": 7,
|
94 |
+
"num_hidden_layers": 12,
|
95 |
+
"num_negatives": 100,
|
96 |
+
"output_hidden_size": 768,
|
97 |
+
"pad_token_id": 0,
|
98 |
+
"proj_codevector_dim": 256,
|
99 |
+
"tdnn_dilation": [
|
100 |
+
1,
|
101 |
+
2,
|
102 |
+
3,
|
103 |
+
1,
|
104 |
+
1
|
105 |
+
],
|
106 |
+
"tdnn_dim": [
|
107 |
+
512,
|
108 |
+
512,
|
109 |
+
512,
|
110 |
+
512,
|
111 |
+
1500
|
112 |
+
],
|
113 |
+
"tdnn_kernel": [
|
114 |
+
5,
|
115 |
+
3,
|
116 |
+
3,
|
117 |
+
1,
|
118 |
+
1
|
119 |
+
],
|
120 |
+
"torch_dtype": "float32",
|
121 |
+
"transformers_version": "4.28.1",
|
122 |
+
"use_weighted_layer_sum": false,
|
123 |
+
"vocab_size": 32,
|
124 |
+
"xvector_output_dim": 512
|
125 |
+
}
|
checkpoint-4170/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2edba1c1b1c3335f4dde03c2ce92c4d1d15d075e9781d1b77c944bad8fecc6c0
|
3 |
+
size 756685669
|
checkpoint-4170/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 |
+
}
|
checkpoint-4170/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20fc433821d61127971c2f1328aab466ca0f311d64a4e7a27282d8e16463dad2
|
3 |
+
size 378352659
|
checkpoint-4170/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0effe8e8564422a13334f56cbe51d52ca56faf8eda558d2721321c8e2f634ea6
|
3 |
+
size 14567
|
checkpoint-4170/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6cd0777cccd29bdb2a14a71f47c31dcf996d37a7a92db4021e5b970902e41bd
|
3 |
+
size 623
|
checkpoint-4170/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4170/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e586ffec83af94e0cf9ea31750e6c3ca1bf1ee016bdd398b7fe339f74b71c58
|
3 |
+
size 3567
|
checkpoint-4865/config.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base-960h",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"Wav2Vec2ForSequenceClassification"
|
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": "sum",
|
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_dropout": 0.0,
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.1,
|
55 |
+
"gradient_checkpointing": false,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_dropout_prob": 0.1,
|
59 |
+
"hidden_size": 768,
|
60 |
+
"id2label": {
|
61 |
+
"0": "english",
|
62 |
+
"1": "spanish",
|
63 |
+
"2": "arabic",
|
64 |
+
"3": "french",
|
65 |
+
"4": "mandarin",
|
66 |
+
"5": "other"
|
67 |
+
},
|
68 |
+
"initializer_range": 0.02,
|
69 |
+
"intermediate_size": 3072,
|
70 |
+
"label2id": {
|
71 |
+
"LABEL_0": 0,
|
72 |
+
"LABEL_1": 1,
|
73 |
+
"LABEL_2": 2,
|
74 |
+
"LABEL_3": 3,
|
75 |
+
"LABEL_4": 4,
|
76 |
+
"LABEL_5": 5
|
77 |
+
},
|
78 |
+
"layer_norm_eps": 1e-05,
|
79 |
+
"layerdrop": 0.1,
|
80 |
+
"mask_feature_length": 10,
|
81 |
+
"mask_feature_min_masks": 0,
|
82 |
+
"mask_feature_prob": 0.0,
|
83 |
+
"mask_time_length": 10,
|
84 |
+
"mask_time_min_masks": 2,
|
85 |
+
"mask_time_prob": 0.05,
|
86 |
+
"model_type": "wav2vec2",
|
87 |
+
"num_adapter_layers": 3,
|
88 |
+
"num_attention_heads": 12,
|
89 |
+
"num_codevector_groups": 2,
|
90 |
+
"num_codevectors_per_group": 320,
|
91 |
+
"num_conv_pos_embedding_groups": 16,
|
92 |
+
"num_conv_pos_embeddings": 128,
|
93 |
+
"num_feat_extract_layers": 7,
|
94 |
+
"num_hidden_layers": 12,
|
95 |
+
"num_negatives": 100,
|
96 |
+
"output_hidden_size": 768,
|
97 |
+
"pad_token_id": 0,
|
98 |
+
"proj_codevector_dim": 256,
|
99 |
+
"tdnn_dilation": [
|
100 |
+
1,
|
101 |
+
2,
|
102 |
+
3,
|
103 |
+
1,
|
104 |
+
1
|
105 |
+
],
|
106 |
+
"tdnn_dim": [
|
107 |
+
512,
|
108 |
+
512,
|
109 |
+
512,
|
110 |
+
512,
|
111 |
+
1500
|
112 |
+
],
|
113 |
+
"tdnn_kernel": [
|
114 |
+
5,
|
115 |
+
3,
|
116 |
+
3,
|
117 |
+
1,
|
118 |
+
1
|
119 |
+
],
|
120 |
+
"torch_dtype": "float32",
|
121 |
+
"transformers_version": "4.28.1",
|
122 |
+
"use_weighted_layer_sum": false,
|
123 |
+
"vocab_size": 32,
|
124 |
+
"xvector_output_dim": 512
|
125 |
+
}
|
checkpoint-4865/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ae7717b96ab29bd0c6e7d2b38e05724da0283a57f33300552cc333c6835b204
|
3 |
+
size 756685669
|
checkpoint-4865/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 |
+
}
|
checkpoint-4865/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43350457b886fe2db874dce5c0917171291e8df554c188a714b3f83dc2e318f8
|
3 |
+
size 378352659
|
checkpoint-4865/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06ef5d41c6f365ce57119eec5e3e504dc3fe79f635b7fcb8536820ebc83c49bd
|
3 |
+
size 14567
|
checkpoint-4865/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de4f5954137b8473313a1edf672c4c4fcf8b7b0eb50b746d28ad259a1199af3f
|
3 |
+
size 623
|
checkpoint-4865/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-4865/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e586ffec83af94e0cf9ea31750e6c3ca1bf1ee016bdd398b7fe339f74b71c58
|
3 |
+
size 3567
|
checkpoint-5560/config.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base-960h",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"adapter_kernel_size": 3,
|
5 |
+
"adapter_stride": 2,
|
6 |
+
"add_adapter": false,
|
7 |
+
"apply_spec_augment": true,
|
8 |
+
"architectures": [
|
9 |
+
"Wav2Vec2ForSequenceClassification"
|
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": "sum",
|
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_dropout": 0.0,
|
51 |
+
"feat_extract_norm": "group",
|
52 |
+
"feat_proj_dropout": 0.1,
|
53 |
+
"feat_quantizer_dropout": 0.0,
|
54 |
+
"final_dropout": 0.1,
|
55 |
+
"gradient_checkpointing": false,
|
56 |
+
"hidden_act": "gelu",
|
57 |
+
"hidden_dropout": 0.1,
|
58 |
+
"hidden_dropout_prob": 0.1,
|
59 |
+
"hidden_size": 768,
|
60 |
+
"id2label": {
|
61 |
+
"0": "english",
|
62 |
+
"1": "spanish",
|
63 |
+
"2": "arabic",
|
64 |
+
"3": "french",
|
65 |
+
"4": "mandarin",
|
66 |
+
"5": "other"
|
67 |
+
},
|
68 |
+
"initializer_range": 0.02,
|
69 |
+
"intermediate_size": 3072,
|
70 |
+
"label2id": {
|
71 |
+
"LABEL_0": 0,
|
72 |
+
"LABEL_1": 1,
|
73 |
+
"LABEL_2": 2,
|
74 |
+
"LABEL_3": 3,
|
75 |
+
"LABEL_4": 4,
|
76 |
+
"LABEL_5": 5
|
77 |
+
},
|
78 |
+
"layer_norm_eps": 1e-05,
|
79 |
+
"layerdrop": 0.1,
|
80 |
+
"mask_feature_length": 10,
|
81 |
+
"mask_feature_min_masks": 0,
|
82 |
+
"mask_feature_prob": 0.0,
|
83 |
+
"mask_time_length": 10,
|
84 |
+
"mask_time_min_masks": 2,
|
85 |
+
"mask_time_prob": 0.05,
|
86 |
+
"model_type": "wav2vec2",
|
87 |
+
"num_adapter_layers": 3,
|
88 |
+
"num_attention_heads": 12,
|
89 |
+
"num_codevector_groups": 2,
|
90 |
+
"num_codevectors_per_group": 320,
|
91 |
+
"num_conv_pos_embedding_groups": 16,
|
92 |
+
"num_conv_pos_embeddings": 128,
|
93 |
+
"num_feat_extract_layers": 7,
|
94 |
+
"num_hidden_layers": 12,
|
95 |
+
"num_negatives": 100,
|
96 |
+
"output_hidden_size": 768,
|
97 |
+
"pad_token_id": 0,
|
98 |
+
"proj_codevector_dim": 256,
|
99 |
+
"tdnn_dilation": [
|
100 |
+
1,
|
101 |
+
2,
|
102 |
+
3,
|
103 |
+
1,
|
104 |
+
1
|
105 |
+
],
|
106 |
+
"tdnn_dim": [
|
107 |
+
512,
|
108 |
+
512,
|
109 |
+
512,
|
110 |
+
512,
|
111 |
+
1500
|
112 |
+
],
|
113 |
+
"tdnn_kernel": [
|
114 |
+
5,
|
115 |
+
3,
|
116 |
+
3,
|
117 |
+
1,
|
118 |
+
1
|
119 |
+
],
|
120 |
+
"torch_dtype": "float32",
|
121 |
+
"transformers_version": "4.28.1",
|
122 |
+
"use_weighted_layer_sum": false,
|
123 |
+
"vocab_size": 32,
|
124 |
+
"xvector_output_dim": 512
|
125 |
+
}
|
checkpoint-5560/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b92110f9394ded1cc7af578211896efd238d978d687f16d50a1001c026f41e6
|
3 |
+
size 756685669
|