Hugging Face's logo

Milana
/
model-classifier-vctk-edacc

Audio Classification
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
Metrics Community
Milana commited on
Commit
c47a470
·
verified ·
1 Parent(s): c373ebf

End of training

Browse files
Files changed (17) hide show
  1. README.md +58 -0
  2. config.json +134 -0
  3. model.safetensors +3 -0
  4. runs/May23_07-41-57_30526c8fffa6/events.out.tfevents.1716450119.30526c8fffa6.298.0 +3 -0
  5. runs/May23_07-42-37_30526c8fffa6/events.out.tfevents.1716450157.30526c8fffa6.298.1 +3 -0
  6. runs/May23_07-43-06_30526c8fffa6/events.out.tfevents.1716450186.30526c8fffa6.298.2 +3 -0
  7. runs/May23_07-43-46_30526c8fffa6/events.out.tfevents.1716450226.30526c8fffa6.298.3 +3 -0
  8. runs/May23_07-44-41_30526c8fffa6/events.out.tfevents.1716450281.30526c8fffa6.298.4 +3 -0
  9. runs/May23_07-48-34_30526c8fffa6/events.out.tfevents.1716450516.30526c8fffa6.4707.0 +3 -0
  10. runs/May23_07-49-49_30526c8fffa6/events.out.tfevents.1716450589.30526c8fffa6.4707.1 +3 -0
  11. runs/May23_07-50-51_30526c8fffa6/events.out.tfevents.1716450653.30526c8fffa6.5669.0 +3 -0
  12. runs/May23_07-57-14_30526c8fffa6/events.out.tfevents.1716451035.30526c8fffa6.5669.1 +3 -0
  13. runs/May23_08-01-03_30526c8fffa6/events.out.tfevents.1716451264.30526c8fffa6.7954.0 +3 -0
  14. runs/May23_10-00-30_30526c8fffa6/events.out.tfevents.1716458431.30526c8fffa6.7954.1 +3 -0
  15. runs/May23_10-08-49_30526c8fffa6/events.out.tfevents.1716458931.30526c8fffa6.38816.0 +3 -0
  16. runs/May23_12-32-57_30526c8fffa6/events.out.tfevents.1716467579.30526c8fffa6.50552.0 +3 -0
  17. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: facebook/mms-lid-4017
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: model-classifier-vctk-edacc
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # model-classifier-vctk-edacc
15
+
16
+ This model is a fine-tuned version of [facebook/mms-lid-4017](https://huggingface.co/facebook/mms-lid-4017) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - eval_loss: 0.9928
19
+ - eval_accuracy: 0.6491
20
+ - eval_runtime: 2565.174
21
+ - eval_samples_per_second: 3.224
22
+ - eval_steps_per_second: 0.403
23
+ - epoch: 0.5
24
+ - step: 200
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 3e-05
44
+ - train_batch_size: 32
45
+ - eval_batch_size: 8
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - training_steps: 400
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Framework versions
54
+
55
+ - Transformers 4.41.0
56
+ - Pytorch 2.3.0+cu121
57
+ - Datasets 2.19.1
58
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mms-lid-4017",
3
+ "activation_dropout": 0.05,
4
+ "adapter_attn_dim": 16,
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": 0.05,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 1024,
15
+ "codevector_dim": 1024,
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": "mean",
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": 0.05,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.05,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.05,
58
+ "hidden_size": 1280,
59
+ "id2label": {
60
+ "0": "LABEL_0",
61
+ "1": "LABEL_1",
62
+ "2": "LABEL_2",
63
+ "3": "LABEL_3",
64
+ "4": "LABEL_4",
65
+ "5": "LABEL_5",
66
+ "6": "LABEL_6",
67
+ "7": "LABEL_7",
68
+ "8": "LABEL_8",
69
+ "9": "LABEL_9",
70
+ "10": "LABEL_10"
71
+ },
72
+ "initializer_range": 0.02,
73
+ "intermediate_size": 5120,
74
+ "label2id": {
75
+ "LABEL_0": 0,
76
+ "LABEL_1": 1,
77
+ "LABEL_10": 10,
78
+ "LABEL_2": 2,
79
+ "LABEL_3": 3,
80
+ "LABEL_4": 4,
81
+ "LABEL_5": 5,
82
+ "LABEL_6": 6,
83
+ "LABEL_7": 7,
84
+ "LABEL_8": 8,
85
+ "LABEL_9": 9
86
+ },
87
+ "layer_norm_eps": 1e-05,
88
+ "layerdrop": 0.05,
89
+ "mask_feature_length": 10,
90
+ "mask_feature_min_masks": 0,
91
+ "mask_feature_prob": 0.0,
92
+ "mask_time_length": 10,
93
+ "mask_time_min_masks": 2,
94
+ "mask_time_prob": 0.05,
95
+ "model_type": "wav2vec2",
96
+ "num_adapter_layers": 3,
97
+ "num_attention_heads": 16,
98
+ "num_codevector_groups": 2,
99
+ "num_codevectors_per_group": 320,
100
+ "num_conv_pos_embedding_groups": 16,
101
+ "num_conv_pos_embeddings": 128,
102
+ "num_feat_extract_layers": 7,
103
+ "num_hidden_layers": 48,
104
+ "num_negatives": 100,
105
+ "output_hidden_size": 1280,
106
+ "pad_token_id": 0,
107
+ "proj_codevector_dim": 1024,
108
+ "tdnn_dilation": [
109
+ 1,
110
+ 2,
111
+ 3,
112
+ 1,
113
+ 1
114
+ ],
115
+ "tdnn_dim": [
116
+ 512,
117
+ 512,
118
+ 512,
119
+ 512,
120
+ 1500
121
+ ],
122
+ "tdnn_kernel": [
123
+ 5,
124
+ 3,
125
+ 3,
126
+ 1,
127
+ 1
128
+ ],
129
+ "torch_dtype": "float32",
130
+ "transformers_version": "4.41.0",
131
+ "use_weighted_layer_sum": false,
132
+ "vocab_size": 154,
133
+ "xvector_output_dim": 512
134
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c16c0778ca3410132d0f4caae91cafa3565c83420cbb073ca68fc09c6a38abf9
3
+ size 3864024348
runs/May23_07-41-57_30526c8fffa6/events.out.tfevents.1716450119.30526c8fffa6.298.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c4facb22401482fb3409d7714efd3564e55f47a6e118c465cefeadd36923e6
3
+ size 7830
runs/May23_07-42-37_30526c8fffa6/events.out.tfevents.1716450157.30526c8fffa6.298.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ca801b770491fac86fd0b3936efaac6294bc79e74ae75d99ac69e62feb390b4
3
+ size 7830
runs/May23_07-43-06_30526c8fffa6/events.out.tfevents.1716450186.30526c8fffa6.298.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43cf3ae30a493e552a1cdd01107f48a7962cdb82877b8e92fed360de55692280
3
+ size 7830
runs/May23_07-43-46_30526c8fffa6/events.out.tfevents.1716450226.30526c8fffa6.298.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ccd91aee4f4c216c0936604a68cb07e7d5a578f10536c2c5e5da3968103a160
3
+ size 7830
runs/May23_07-44-41_30526c8fffa6/events.out.tfevents.1716450281.30526c8fffa6.298.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a40cbca97e641fa9a5c4578d07b778e0c647cebaa73f57a6d1e2a39be01d7800
3
+ size 6738
runs/May23_07-48-34_30526c8fffa6/events.out.tfevents.1716450516.30526c8fffa6.4707.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb11e206e58e9f36be625f0ad65a16cc519b24f8f8fc53087e87b283a234618f
3
+ size 4184
runs/May23_07-49-49_30526c8fffa6/events.out.tfevents.1716450589.30526c8fffa6.4707.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26e530b965d35c32f6dff07e9d85e7da1747d6eb745a6930c3e5796b489b8704
3
+ size 4184
runs/May23_07-50-51_30526c8fffa6/events.out.tfevents.1716450653.30526c8fffa6.5669.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1c462d45d3afa8a1a20c7e2350a058c0ebd313c38815dc24f530301e3575427
3
+ size 7086
runs/May23_07-57-14_30526c8fffa6/events.out.tfevents.1716451035.30526c8fffa6.5669.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae54779e16c28bd7ae19f8d0da9c56c9d04d2b16b761d6a6d25c3b5b0007747e
3
+ size 4184
runs/May23_08-01-03_30526c8fffa6/events.out.tfevents.1716451264.30526c8fffa6.7954.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0298b203c5471869b544ffb1d89e4c930ffac548f84099209f7440ec9063c6d
3
+ size 7474
runs/May23_10-00-30_30526c8fffa6/events.out.tfevents.1716458431.30526c8fffa6.7954.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:883dcc860e15a288408bfc8dd67b6c64baf622361fd070d4619dbbd3d8e5e539
3
+ size 4184
runs/May23_10-08-49_30526c8fffa6/events.out.tfevents.1716458931.30526c8fffa6.38816.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea63bf85e2b589e7a228046916fcbb71a43941bf3450b517c9f8940f85f2fdc7
3
+ size 6946
runs/May23_12-32-57_30526c8fffa6/events.out.tfevents.1716467579.30526c8fffa6.50552.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:739b5c04a45652637fac6ad3cbd7259a6f7af48b710704341d24432bd222e574
3
+ size 8008
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:879edb882ab18f92ec725b1e67474960f0ba450b22b256d077d077a97b78bc55
3
+ size 5112