Hugging Face's logo

butuskapes
/
hubert

TensorBoard
Safetensors
hubert
Model card Files
xet
 Metrics Community
butuskapes commited on
Commit
425ca7b
·
verified ·
1 Parent(s): 5bbe629

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. config.json +8 -42
  2. model.safetensors +2 -2
  3. preprocessor_config.json +2 -2
  4. runs/Jun29_12-54-12_gl1703.arc-ts.umich.edu/events.out.tfevents.1751217911.gl1703.arc-ts.umich.edu.1223681.0 +2 -2
  5. runs/Jun29_14-34-35_gl1703.arc-ts.umich.edu/events.out.tfevents.1751222078.gl1703.arc-ts.umich.edu.1263527.0 +3 -0
  6. training_args.bin +1 -1
config.json CHANGED
@@ -1,20 +1,14 @@
1
  {
2
- "_name_or_path": "facebook/wav2vec2-large",
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
- "Wav2Vec2ForSequenceClassification"
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": false,
18
  "conv_dim": [
19
  512,
20
  512,
@@ -45,13 +39,13 @@
45
  "ctc_loss_reduction": "sum",
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",
@@ -94,43 +88,15 @@
94
  "mask_time_length": 10,
95
  "mask_time_min_masks": 2,
96
  "mask_time_prob": 0.05,
97
- "model_type": "wav2vec2",
98
- "num_adapter_layers": 3,
99
  "num_attention_heads": 16,
100
- "num_codevector_groups": 2,
101
- "num_codevectors_per_group": 320,
102
  "num_conv_pos_embedding_groups": 16,
103
  "num_conv_pos_embeddings": 128,
104
  "num_feat_extract_layers": 7,
105
  "num_hidden_layers": 24,
106
- "num_negatives": 100,
107
- "output_hidden_size": 1024,
108
  "pad_token_id": 0,
109
- "proj_codevector_dim": 768,
110
- "tdnn_dilation": [
111
- 1,
112
- 2,
113
- 3,
114
- 1,
115
- 1
116
- ],
117
- "tdnn_dim": [
118
- 512,
119
- 512,
120
- 512,
121
- 512,
122
- 1500
123
- ],
124
- "tdnn_kernel": [
125
- 5,
126
- 3,
127
- 3,
128
- 1,
129
- 1
130
- ],
131
  "torch_dtype": "float32",
132
  "transformers_version": "4.46.2",
133
  "use_weighted_layer_sum": false,
134
- "vocab_size": 32,
135
- "xvector_output_dim": 512
136
  }
 
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",
 
88
  "mask_time_length": 10,
89
  "mask_time_min_masks": 2,
90
  "mask_time_prob": 0.05,
91
+ "model_type": "hubert",
 
92
  "num_attention_heads": 16,
 
 
93
  "num_conv_pos_embedding_groups": 16,
94
  "num_conv_pos_embeddings": 128,
95
  "num_feat_extract_layers": 7,
96
  "num_hidden_layers": 24,
 
 
97
  "pad_token_id": 0,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98
  "torch_dtype": "float32",
99
  "transformers_version": "4.46.2",
100
  "use_weighted_layer_sum": false,
101
+ "vocab_size": 32
 
102
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe3ce4d0d0997cd5e5db3f03c8c4706dcd6bd78f5e59fb2fc1aa3abd96f2b2c3
3
- size 1262827244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e1be150bed68ea35da7ab1a5f6f0f9e440e5d9449eeddf3cfd374ea8842c292
3
+ size 1262867716
preprocessor_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
  "feature_size": 1,
5
  "padding_side": "right",
6
- "padding_value": 0.0,
7
- "return_attention_mask": false,
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/Jun29_12-54-12_gl1703.arc-ts.umich.edu/events.out.tfevents.1751217911.gl1703.arc-ts.umich.edu.1223681.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5544fcea14844c2f78b1c81b070e51d6e889adaecacb8262b1ab6d320e20ba13
3
- size 26817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:404cc31040f728501cc5ffeeb904960649e579c9589689ee3a0ec0ed9a4eff23
3
+ size 27872
runs/Jun29_14-34-35_gl1703.arc-ts.umich.edu/events.out.tfevents.1751222078.gl1703.arc-ts.umich.edu.1263527.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f558b0915a46f56f893c0bdd3e6c5714e94a8c7f757bf6c35b42b03f7f20b8bc
3
+ size 13431
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:742712ff1026cfd185052c684ecb47e7d898f7776901a1f257f255332e20d9d7
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aa495564645c2202dc5c1a505f12e02619d2a572aa91a1cb008e64367c5448a
3
  size 5304