Hugging Face's logo

seemdog
/
ManWav

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Inference Endpoints
Model card Files Community
seemdog commited on
Commit
465c66c
•
1 Parent(s): b4a02e4

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +117 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +79 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
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
+ "Wav2Vec2ForCTC"
11
+ ],
12
+ "attention_dropout": 0.1,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 768,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "sum",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.1,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.1,
59
+ "hidden_size": 1024,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 4096,
62
+ "layer_norm_eps": 1e-05,
63
+ "layerdrop": 0.0,
64
+ "mask_channel_length": 10,
65
+ "mask_channel_min_space": 1,
66
+ "mask_channel_other": 0.0,
67
+ "mask_channel_prob": 0.0,
68
+ "mask_channel_selection": "static",
69
+ "mask_feature_length": 10,
70
+ "mask_feature_min_masks": 0,
71
+ "mask_feature_prob": 0.0,
72
+ "mask_time_length": 10,
73
+ "mask_time_min_masks": 2,
74
+ "mask_time_min_space": 1,
75
+ "mask_time_other": 0.0,
76
+ "mask_time_prob": 0.05,
77
+ "mask_time_selection": "static",
78
+ "model_type": "wav2vec2",
79
+ "num_adapter_layers": 3,
80
+ "num_attention_heads": 16,
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": 24,
87
+ "num_negatives": 100,
88
+ "output_hidden_size": 1024,
89
+ "pad_token_id": 32,
90
+ "proj_codevector_dim": 768,
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": "4.35.2",
114
+ "use_weighted_layer_sum": false,
115
+ "vocab_size": 37,
116
+ "xvector_output_dim": 512
117
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17b81b630366cd7b9d573c8f786da674c64723685c11275799c67ec90ba6cf36
3
+ size 1261959132
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f49d092e4fbe9a6dd9d2ec827a157394b49e9a716befd55fea70099799ff3e1e
3
+ size 2490362385
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cae70758c9f2d79612a209894ade12685ac080832f127585b06bd9c35cdbc52
3
+ size 14567
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806870f511dd94ffa0b691855f3ed250608e036a0d79d391e9518bba27bcc331
3
+ size 623
trainer_state.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.149377593360996,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.41,
13
+ "learning_rate": 0.0002,
14
+ "loss": 5302.2344,
15
+ "step": 100
16
+ },
17
+ {
18
+ "epoch": 0.83,
19
+ "learning_rate": 0.0002,
20
+ "loss": 2147.5883,
21
+ "step": 200
22
+ },
23
+ {
24
+ "epoch": 1.24,
25
+ "learning_rate": 0.0002,
26
+ "loss": 2079.1225,
27
+ "step": 300
28
+ },
29
+ {
30
+ "epoch": 1.66,
31
+ "learning_rate": 0.0002,
32
+ "loss": 924.7552,
33
+ "step": 400
34
+ },
35
+ {
36
+ "epoch": 2.07,
37
+ "learning_rate": 0.0002,
38
+ "loss": 468.9583,
39
+ "step": 500
40
+ },
41
+ {
42
+ "epoch": 2.49,
43
+ "learning_rate": 0.0002,
44
+ "loss": 365.4921,
45
+ "step": 600
46
+ },
47
+ {
48
+ "epoch": 2.9,
49
+ "learning_rate": 0.0002,
50
+ "loss": 293.9367,
51
+ "step": 700
52
+ },
53
+ {
54
+ "epoch": 3.32,
55
+ "learning_rate": 0.0002,
56
+ "loss": 236.9112,
57
+ "step": 800
58
+ },
59
+ {
60
+ "epoch": 3.73,
61
+ "learning_rate": 0.0002,
62
+ "loss": 211.7118,
63
+ "step": 900
64
+ },
65
+ {
66
+ "epoch": 4.15,
67
+ "learning_rate": 0.0002,
68
+ "loss": 159.076,
69
+ "step": 1000
70
+ }
71
+ ],
72
+ "logging_steps": 100,
73
+ "max_steps": 1205,
74
+ "num_train_epochs": 5,
75
+ "save_steps": 500,
76
+ "total_flos": 3.294404741029474e+18,
77
+ "trial_name": null,
78
+ "trial_params": null
79
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ccfafe9fc28154b196cbe8eb4bf3c735e0d213d8dfb7bafceccec0e666b97d6
3
+ size 4079