Hugging Face's logo

Bgeorge
/
model_dialect

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Bgeorge commited on
Commit
6a634c8
•
1 Parent(s): 76438ba

Training in progress, epoch 0

Browse files
Files changed (4) hide show
  1. config.json +117 -24
  2. model.safetensors +2 -2
  3. runs/Oct27_20-22-49_dd2cd04d617b/events.out.tfevents.1730060571.dd2cd04d617b.23.0 +3 -0
  4. training_args.bin +2 -2
config.json CHANGED
@@ -1,39 +1,132 @@
1
  {
2
- "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
 
 
 
 
 
 
3
  "architectures": [
4
- "ASTForAudioClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.0,
7
- "frequency_stride": 10,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.0,
10
  "hidden_size": 768,
11
  "id2label": {
12
- "0": "Muntenesc",
13
- "1": "Oltenesc",
14
- "2": "Moldovenesc",
15
- "3": "Ardelenesc",
16
- "4": "Banatean"
17
  },
18
  "initializer_range": 0.02,
19
  "intermediate_size": 3072,
20
  "label2id": {
21
- "Ardelenesc": "3",
22
- "Banatean": "4",
23
- "Moldovenesc": "2",
24
- "Muntenesc": "0",
25
- "Oltenesc": "1"
26
  },
27
- "layer_norm_eps": 1e-12,
28
- "max_length": 1024,
29
- "model_type": "audio-spectrogram-transformer",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  "num_attention_heads": 12,
 
 
 
 
 
31
  "num_hidden_layers": 12,
32
- "num_mel_bins": 128,
33
- "patch_size": 16,
34
- "problem_type": "single_label_classification",
35
- "qkv_bias": true,
36
- "time_stride": 10,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  "torch_dtype": "float32",
38
- "transformers_version": "4.45.1"
 
 
 
39
  }
 
1
  {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
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": 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": "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_norm": "group",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "freeze_feat_extract_train": true,
56
  "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
  "hidden_size": 768,
59
  "id2label": {
60
+ "0": "Oltenesc",
61
+ "1": "Ardelenesc",
62
+ "2": "Muntenesc",
63
+ "3": "Banatean",
64
+ "4": "Moldovenesc"
65
  },
66
  "initializer_range": 0.02,
67
  "intermediate_size": 3072,
68
  "label2id": {
69
+ "Ardelenesc": "1",
70
+ "Banatean": "3",
71
+ "Moldovenesc": "4",
72
+ "Muntenesc": "2",
73
+ "Oltenesc": "0"
74
  },
75
+ "layer_norm_eps": 1e-05,
76
+ "layerdrop": 0.0,
77
+ "mask_channel_length": 10,
78
+ "mask_channel_min_space": 1,
79
+ "mask_channel_other": 0.0,
80
+ "mask_channel_prob": 0.0,
81
+ "mask_channel_selection": "static",
82
+ "mask_feature_length": 10,
83
+ "mask_feature_min_masks": 0,
84
+ "mask_feature_prob": 0.0,
85
+ "mask_time_length": 10,
86
+ "mask_time_min_masks": 2,
87
+ "mask_time_min_space": 1,
88
+ "mask_time_other": 0.0,
89
+ "mask_time_prob": 0.05,
90
+ "mask_time_selection": "static",
91
+ "model_type": "wav2vec2",
92
+ "no_mask_channel_overlap": false,
93
+ "no_mask_time_overlap": false,
94
+ "num_adapter_layers": 3,
95
  "num_attention_heads": 12,
96
+ "num_codevector_groups": 2,
97
+ "num_codevectors_per_group": 320,
98
+ "num_conv_pos_embedding_groups": 16,
99
+ "num_conv_pos_embeddings": 128,
100
+ "num_feat_extract_layers": 7,
101
  "num_hidden_layers": 12,
102
+ "num_negatives": 100,
103
+ "output_hidden_size": 768,
104
+ "pad_token_id": 0,
105
+ "proj_codevector_dim": 256,
106
+ "tdnn_dilation": [
107
+ 1,
108
+ 2,
109
+ 3,
110
+ 1,
111
+ 1
112
+ ],
113
+ "tdnn_dim": [
114
+ 512,
115
+ 512,
116
+ 512,
117
+ 512,
118
+ 1500
119
+ ],
120
+ "tdnn_kernel": [
121
+ 5,
122
+ 3,
123
+ 3,
124
+ 1,
125
+ 1
126
+ ],
127
  "torch_dtype": "float32",
128
+ "transformers_version": "4.46.0",
129
+ "use_weighted_layer_sum": false,
130
+ "vocab_size": 32,
131
+ "xvector_output_dim": 512
132
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe21f07172b8a80133a2745f481746cfe2fdc8efb460d0f32ce4f22b3dd916f4
3
- size 344799268
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c568b8d3ba18fc86c2807be09c966e83b78b768590dbb3f2a73aa3d3b3fd1c1e
3
+ size 378305452
runs/Oct27_20-22-49_dd2cd04d617b/events.out.tfevents.1730060571.dd2cd04d617b.23.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:336b9023fea76c82c22ed0d7d95d826bd0204e518c7ac5a6c95e41fba1012fa9
3
+ size 7563
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:787577a2cb16f9d220e6e51990b03a71b2dd083e4fbca2f82efa8754893ef521
3
- size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0da0b2b5bf3429c0edce6778e0591ebb5c1e5ea18d09dd6a1be4e444e9d26a99
3
+ size 5304