Hugging Face's logo

jadorantes2
/
my_awesome_asr_mind_model

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Model card Files Metrics Community
jadorantes2 commited on
Commit
24b7f97
·
verified ·
1 Parent(s): e6658f5

Training in progress, step 1000

Browse files
Files changed (5) hide show
  1. config.json +110 -82
  2. model.safetensors +2 -2
  3. preprocessor_config.json +10 -11
  4. runs/Jul22_15-17-05_Juan/events.out.tfevents.1721683049.Juan.14724.0 +3 -0
  5. training_args.bin +2 -2
config.json CHANGED
@@ -1,82 +1,110 @@
1
- {
2
- "_name_or_path": "facebook/w2v-bert-2.0",
3
- "activation_dropout": 0.0,
4
- "adapter_act": "relu",
5
- "adapter_kernel_size": 3,
6
- "adapter_stride": 2,
7
- "add_adapter": true,
8
- "apply_spec_augment": false,
9
- "architectures": [
10
- "Wav2Vec2BertForCTC"
11
- ],
12
- "attention_dropout": 0.0,
13
- "bos_token_id": 1,
14
- "classifier_proj_size": 768,
15
- "codevector_dim": 768,
16
- "conformer_conv_dropout": 0.1,
17
- "contrastive_logits_temperature": 0.1,
18
- "conv_depthwise_kernel_size": 31,
19
- "ctc_loss_reduction": "mean",
20
- "ctc_zero_infinity": false,
21
- "diversity_loss_weight": 0.1,
22
- "eos_token_id": 2,
23
- "feat_proj_dropout": 0.0,
24
- "feat_quantizer_dropout": 0.0,
25
- "feature_projection_input_dim": 160,
26
- "final_dropout": 0.1,
27
- "hidden_act": "swish",
28
- "hidden_dropout": 0.0,
29
- "hidden_size": 1024,
30
- "initializer_range": 0.02,
31
- "intermediate_size": 4096,
32
- "layer_norm_eps": 1e-05,
33
- "layerdrop": 0.0,
34
- "left_max_position_embeddings": 64,
35
- "mask_feature_length": 10,
36
- "mask_feature_min_masks": 0,
37
- "mask_feature_prob": 0.0,
38
- "mask_time_length": 10,
39
- "mask_time_min_masks": 2,
40
- "mask_time_prob": 0.0,
41
- "max_source_positions": 5000,
42
- "model_type": "wav2vec2-bert",
43
- "num_adapter_layers": 1,
44
- "num_attention_heads": 16,
45
- "num_codevector_groups": 2,
46
- "num_codevectors_per_group": 320,
47
- "num_hidden_layers": 24,
48
- "num_negatives": 100,
49
- "output_hidden_size": 1024,
50
- "pad_token_id": 28,
51
- "position_embeddings_type": "relative_key",
52
- "proj_codevector_dim": 768,
53
- "right_max_position_embeddings": 8,
54
- "rotary_embedding_base": 10000,
55
- "tdnn_dilation": [
56
- 1,
57
- 2,
58
- 3,
59
- 1,
60
- 1
61
- ],
62
- "tdnn_dim": [
63
- 512,
64
- 512,
65
- 512,
66
- 512,
67
- 1500
68
- ],
69
- "tdnn_kernel": [
70
- 5,
71
- 3,
72
- 3,
73
- 1,
74
- 1
75
- ],
76
- "torch_dtype": "float32",
77
- "transformers_version": "4.40.2",
78
- "use_intermediate_ffn_before_adapter": false,
79
- "use_weighted_layer_sum": false,
80
- "vocab_size": 31,
81
- "xvector_output_dim": 512
82
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base-960h",
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": 256,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": false,
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": "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": 0.1,
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_dropout_prob": 0.1,
60
+ "hidden_size": 768,
61
+ "initializer_range": 0.02,
62
+ "intermediate_size": 3072,
63
+ "layer_norm_eps": 1e-05,
64
+ "layerdrop": 0.1,
65
+ "mask_feature_length": 10,
66
+ "mask_feature_min_masks": 0,
67
+ "mask_feature_prob": 0.0,
68
+ "mask_time_length": 10,
69
+ "mask_time_min_masks": 2,
70
+ "mask_time_prob": 0.05,
71
+ "model_type": "wav2vec2",
72
+ "num_adapter_layers": 3,
73
+ "num_attention_heads": 12,
74
+ "num_codevector_groups": 2,
75
+ "num_codevectors_per_group": 320,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 12,
80
+ "num_negatives": 100,
81
+ "output_hidden_size": 768,
82
+ "pad_token_id": 0,
83
+ "proj_codevector_dim": 256,
84
+ "tdnn_dilation": [
85
+ 1,
86
+ 2,
87
+ 3,
88
+ 1,
89
+ 1
90
+ ],
91
+ "tdnn_dim": [
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 512,
96
+ 1500
97
+ ],
98
+ "tdnn_kernel": [
99
+ 5,
100
+ 3,
101
+ 3,
102
+ 1,
103
+ 1
104
+ ],
105
+ "torch_dtype": "float32",
106
+ "transformers_version": "4.42.3",
107
+ "use_weighted_layer_sum": false,
108
+ "vocab_size": 32,
109
+ "xvector_output_dim": 512
110
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3de3f77fa955517c0d12da2d791667992604a4c69a216487fa2e30c700220a54
3
- size 2422941660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9a82c893be5be84ed06589ff2dbbcc23566a56426c7d88304f95af023baf9e2
3
+ size 377611120
preprocessor_config.json CHANGED
@@ -1,11 +1,10 @@
1
- {
2
- "feature_extractor_type": "SeamlessM4TFeatureExtractor",
3
- "feature_size": 80,
4
- "num_mel_bins": 80,
5
- "padding_side": "right",
6
- "padding_value": 1,
7
- "processor_class": "Wav2Vec2BertProcessor",
8
- "return_attention_mask": true,
9
- "sampling_rate": 16000,
10
- "stride": 2
11
- }
 
1
+ {
2
+ "do_normalize": true,
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
+ }
 
runs/Jul22_15-17-05_Juan/events.out.tfevents.1721683049.Juan.14724.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e68e8d2759ad34a6407cff0a0e735f32bc4aa202b6e640de81d0c5b5e704bac
3
+ size 15051
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caf329b4cb348aba7015fb624f5023ebc95d877c4d861b8d1c565ad950262c0f
3
- size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:557979562b7e096fb8854a16f64fb1ca908650d07386447e4cde3a68dc3c26cc
3
+ size 5112