Hugging Face's logo

Bagus
/
wav2vec2_swbd_emodb

Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
Bagus commited on
Commit
33b3288
·
verified ·
1 Parent(s): ad7bb2e

Model save

Browse files
Files changed (2) hide show
  1. README.md +120 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-large-robust-ft-swbd-300h
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: finetuned
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
+ # finetuned
15
+
16
+ This model is a fine-tuned version of [facebook/wav2vec2-large-robust-ft-swbd-300h](https://huggingface.co/facebook/wav2vec2-large-robust-ft-swbd-300h) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.0281
19
+ - Uar: 0.7318
20
+ - Acc: 0.7721
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0001
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 4
44
+ - total_train_batch_size: 32
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 10
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Uar | Acc |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
53
+ | No log | 0.15 | 1 | 1.3899 | 0.25 | 0.1985 |
54
+ | No log | 0.31 | 2 | 1.3850 | 0.25 | 0.1985 |
55
+ | No log | 0.46 | 3 | 1.3815 | 0.25 | 0.1985 |
56
+ | No log | 0.62 | 4 | 1.3772 | 0.25 | 0.1985 |
57
+ | No log | 0.77 | 5 | 1.3714 | 0.25 | 0.4044 |
58
+ | No log | 0.92 | 6 | 1.3656 | 0.25 | 0.4044 |
59
+ | 1.4878 | 1.08 | 7 | 1.3610 | 0.25 | 0.4044 |
60
+ | 1.4878 | 1.23 | 8 | 1.3583 | 0.25 | 0.4044 |
61
+ | 1.4878 | 1.38 | 9 | 1.3549 | 0.25 | 0.4044 |
62
+ | 1.4878 | 1.54 | 10 | 1.3518 | 0.25 | 0.4044 |
63
+ | 1.4878 | 1.69 | 11 | 1.3491 | 0.25 | 0.4044 |
64
+ | 1.4878 | 1.85 | 12 | 1.3458 | 0.25 | 0.4044 |
65
+ | 1.4878 | 2.0 | 13 | 1.3425 | 0.25 | 0.4044 |
66
+ | 1.2316 | 2.15 | 14 | 1.3401 | 0.25 | 0.4044 |
67
+ | 1.2316 | 2.31 | 15 | 1.3380 | 0.25 | 0.4044 |
68
+ | 1.2316 | 2.46 | 16 | 1.3354 | 0.25 | 0.4044 |
69
+ | 1.2316 | 2.62 | 17 | 1.3326 | 0.25 | 0.4044 |
70
+ | 1.2316 | 2.77 | 18 | 1.3292 | 0.2778 | 0.4265 |
71
+ | 1.2316 | 2.92 | 19 | 1.3250 | 0.2963 | 0.4412 |
72
+ | 1.3835 | 3.08 | 20 | 1.3212 | 0.3519 | 0.4853 |
73
+ | 1.3835 | 3.23 | 21 | 1.3158 | 0.4029 | 0.5221 |
74
+ | 1.3835 | 3.38 | 22 | 1.3096 | 0.5047 | 0.6029 |
75
+ | 1.3835 | 3.54 | 23 | 1.3019 | 0.5695 | 0.6544 |
76
+ | 1.3835 | 3.69 | 24 | 1.2944 | 0.6485 | 0.7059 |
77
+ | 1.3835 | 3.85 | 25 | 1.2856 | 0.6534 | 0.6985 |
78
+ | 1.3835 | 4.0 | 26 | 1.2773 | 0.6768 | 0.7059 |
79
+ | 1.1038 | 4.15 | 27 | 1.2688 | 0.6540 | 0.6691 |
80
+ | 1.1038 | 4.31 | 28 | 1.2554 | 0.6404 | 0.6471 |
81
+ | 1.1038 | 4.46 | 29 | 1.2404 | 0.6359 | 0.6397 |
82
+ | 1.1038 | 4.62 | 30 | 1.2222 | 0.6586 | 0.6765 |
83
+ | 1.1038 | 4.77 | 31 | 1.2057 | 0.6631 | 0.6838 |
84
+ | 1.1038 | 4.92 | 32 | 1.1874 | 0.6769 | 0.6985 |
85
+ | 1.075 | 5.08 | 33 | 1.1624 | 0.6953 | 0.7206 |
86
+ | 1.075 | 5.23 | 34 | 1.1427 | 0.7182 | 0.75 |
87
+ | 1.075 | 5.38 | 35 | 1.1270 | 0.7182 | 0.75 |
88
+ | 1.075 | 5.54 | 36 | 1.1085 | 0.7227 | 0.7574 |
89
+ | 1.075 | 5.69 | 37 | 1.0982 | 0.7227 | 0.7574 |
90
+ | 1.075 | 5.85 | 38 | 1.0943 | 0.7227 | 0.7574 |
91
+ | 1.075 | 6.0 | 39 | 1.0930 | 0.7136 | 0.7426 |
92
+ | 0.7211 | 6.15 | 40 | 1.0903 | 0.7091 | 0.7353 |
93
+ | 0.7211 | 6.31 | 41 | 1.0858 | 0.7091 | 0.7353 |
94
+ | 0.7211 | 6.46 | 42 | 1.0816 | 0.7045 | 0.7279 |
95
+ | 0.7211 | 6.62 | 43 | 1.0734 | 0.7091 | 0.7353 |
96
+ | 0.7211 | 6.77 | 44 | 1.0617 | 0.7136 | 0.7426 |
97
+ | 0.7211 | 6.92 | 45 | 1.0536 | 0.7136 | 0.7426 |
98
+ | 0.6595 | 7.08 | 46 | 1.0450 | 0.7318 | 0.7721 |
99
+ | 0.6595 | 7.23 | 47 | 1.0370 | 0.7364 | 0.7794 |
100
+ | 0.6595 | 7.38 | 48 | 1.0323 | 0.7364 | 0.7794 |
101
+ | 0.6595 | 7.54 | 49 | 1.0301 | 0.7364 | 0.7794 |
102
+ | 0.6595 | 7.69 | 50 | 1.0307 | 0.7364 | 0.7794 |
103
+ | 0.6595 | 7.85 | 51 | 1.0302 | 0.7318 | 0.7721 |
104
+ | 0.6595 | 8.0 | 52 | 1.0307 | 0.7318 | 0.7721 |
105
+ | 0.5067 | 8.15 | 53 | 1.0317 | 0.7318 | 0.7721 |
106
+ | 0.5067 | 8.31 | 54 | 1.0324 | 0.7318 | 0.7721 |
107
+ | 0.5067 | 8.46 | 55 | 1.0324 | 0.7318 | 0.7721 |
108
+ | 0.5067 | 8.62 | 56 | 1.0326 | 0.7273 | 0.7647 |
109
+ | 0.5067 | 8.77 | 57 | 1.0315 | 0.7318 | 0.7721 |
110
+ | 0.5067 | 8.92 | 58 | 1.0297 | 0.7318 | 0.7721 |
111
+ | 0.5617 | 9.08 | 59 | 1.0287 | 0.7318 | 0.7721 |
112
+ | 0.5617 | 9.23 | 60 | 1.0281 | 0.7318 | 0.7721 |
113
+
114
+
115
+ ### Framework versions
116
+
117
+ - Transformers 4.32.0
118
+ - Pytorch 2.3.0+cu121
119
+ - Datasets 2.19.1
120
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31527d34bea81db26c3780914bd49bda7438e11b5f61eb252c68b79c378d9e42
3
  size 1266117810
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba2316fc9d94c6d8c6f07f6333d2530247afa416539d79010b0680a3042efb76
3
  size 1266117810