End of training
Browse files
README.md
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: jadasdn/wav2vec2-1
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
+
model-index:
|
9 |
+
- name: wav2vec2-2
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# wav2vec2-2
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [jadasdn/wav2vec2-1](https://huggingface.co/jadasdn/wav2vec2-1) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.8353
|
21 |
+
- Wer: 0.3593
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0001
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_steps: 1000
|
47 |
+
- num_epochs: 30
|
48 |
+
- mixed_precision_training: Native AMP
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
54 |
+
| 0.4516 | 0.5 | 500 | 0.4973 | 0.3748 |
|
55 |
+
| 0.4624 | 1.0 | 1000 | 0.4486 | 0.3958 |
|
56 |
+
| 0.5211 | 1.5 | 1500 | 0.5173 | 0.3916 |
|
57 |
+
| 0.5317 | 2.0 | 2000 | 0.4713 | 0.3992 |
|
58 |
+
| 0.4277 | 2.5 | 2500 | 0.4859 | 0.3888 |
|
59 |
+
| 0.4495 | 3.0 | 3000 | 0.4962 | 0.3862 |
|
60 |
+
| 0.3712 | 3.5 | 3500 | 0.5237 | 0.3899 |
|
61 |
+
| 0.3855 | 4.0 | 4000 | 0.4975 | 0.3850 |
|
62 |
+
| 0.3254 | 4.5 | 4500 | 0.5405 | 0.3897 |
|
63 |
+
| 0.331 | 5.0 | 5000 | 0.5255 | 0.3950 |
|
64 |
+
| 0.2907 | 5.5 | 5500 | 0.5646 | 0.3852 |
|
65 |
+
| 0.2949 | 6.0 | 6000 | 0.5782 | 0.3965 |
|
66 |
+
| 0.2521 | 6.5 | 6500 | 0.5563 | 0.3879 |
|
67 |
+
| 0.2663 | 7.0 | 7000 | 0.5627 | 0.3829 |
|
68 |
+
| 0.2342 | 7.5 | 7500 | 0.6145 | 0.3872 |
|
69 |
+
| 0.2374 | 8.0 | 8000 | 0.5860 | 0.3883 |
|
70 |
+
| 0.2099 | 8.5 | 8500 | 0.6920 | 0.3810 |
|
71 |
+
| 0.2133 | 9.0 | 9000 | 0.6354 | 0.3895 |
|
72 |
+
| 0.1887 | 9.5 | 9500 | 0.6618 | 0.3813 |
|
73 |
+
| 0.1924 | 10.0 | 10000 | 0.6522 | 0.3850 |
|
74 |
+
| 0.1728 | 10.5 | 10500 | 0.6324 | 0.3813 |
|
75 |
+
| 0.1797 | 11.0 | 11000 | 0.6637 | 0.3882 |
|
76 |
+
| 0.163 | 11.5 | 11500 | 0.6806 | 0.3799 |
|
77 |
+
| 0.1623 | 12.0 | 12000 | 0.6801 | 0.3811 |
|
78 |
+
| 0.149 | 12.5 | 12500 | 0.6723 | 0.3832 |
|
79 |
+
| 0.1493 | 13.0 | 13000 | 0.7032 | 0.3888 |
|
80 |
+
| 0.1389 | 13.5 | 13500 | 0.7294 | 0.3793 |
|
81 |
+
| 0.1383 | 14.0 | 14000 | 0.7311 | 0.3800 |
|
82 |
+
| 0.127 | 14.5 | 14500 | 0.7088 | 0.3773 |
|
83 |
+
| 0.127 | 15.0 | 15000 | 0.7352 | 0.3775 |
|
84 |
+
| 0.1159 | 15.5 | 15500 | 0.7886 | 0.3792 |
|
85 |
+
| 0.114 | 16.0 | 16000 | 0.7582 | 0.3802 |
|
86 |
+
| 0.1103 | 16.5 | 16500 | 0.7662 | 0.3717 |
|
87 |
+
| 0.1088 | 17.0 | 17000 | 0.7855 | 0.3704 |
|
88 |
+
| 0.1021 | 17.5 | 17500 | 0.7326 | 0.3717 |
|
89 |
+
| 0.104 | 18.0 | 18000 | 0.7518 | 0.3723 |
|
90 |
+
| 0.096 | 18.5 | 18500 | 0.7468 | 0.3743 |
|
91 |
+
| 0.0914 | 19.0 | 19000 | 0.7906 | 0.3741 |
|
92 |
+
| 0.0881 | 19.5 | 19500 | 0.7879 | 0.3740 |
|
93 |
+
| 0.0908 | 20.0 | 20000 | 0.8111 | 0.3676 |
|
94 |
+
| 0.0832 | 20.5 | 20500 | 0.8114 | 0.3681 |
|
95 |
+
| 0.0848 | 21.0 | 21000 | 0.8178 | 0.3651 |
|
96 |
+
| 0.0762 | 21.5 | 21500 | 0.8212 | 0.3686 |
|
97 |
+
| 0.0728 | 22.0 | 22000 | 0.8142 | 0.3673 |
|
98 |
+
| 0.074 | 22.5 | 22500 | 0.8177 | 0.3666 |
|
99 |
+
| 0.0691 | 23.0 | 23000 | 0.8323 | 0.3662 |
|
100 |
+
| 0.0689 | 23.5 | 23500 | 0.8020 | 0.3678 |
|
101 |
+
| 0.0643 | 24.0 | 24000 | 0.8145 | 0.3653 |
|
102 |
+
| 0.0647 | 24.5 | 24500 | 0.8376 | 0.3594 |
|
103 |
+
| 0.0654 | 25.0 | 25000 | 0.8307 | 0.3608 |
|
104 |
+
| 0.061 | 25.5 | 25500 | 0.8432 | 0.3600 |
|
105 |
+
| 0.0573 | 26.0 | 26000 | 0.8361 | 0.3629 |
|
106 |
+
| 0.0583 | 26.5 | 26500 | 0.8363 | 0.3625 |
|
107 |
+
| 0.054 | 27.0 | 27000 | 0.8277 | 0.3625 |
|
108 |
+
| 0.058 | 27.5 | 27500 | 0.8354 | 0.3614 |
|
109 |
+
| 0.0531 | 28.0 | 28000 | 0.8363 | 0.3595 |
|
110 |
+
| 0.0522 | 28.5 | 28500 | 0.8429 | 0.3588 |
|
111 |
+
| 0.0503 | 29.0 | 29000 | 0.8267 | 0.3595 |
|
112 |
+
| 0.0504 | 29.5 | 29500 | 0.8401 | 0.3597 |
|
113 |
+
| 0.0511 | 30.0 | 30000 | 0.8353 | 0.3593 |
|
114 |
+
|
115 |
+
|
116 |
+
### Framework versions
|
117 |
+
|
118 |
+
- Transformers 4.35.2
|
119 |
+
- Pytorch 2.1.0+cu118
|
120 |
+
- Datasets 2.15.0
|
121 |
+
- Tokenizers 0.15.0
|