Update README.md
Browse files
README.md
CHANGED
@@ -36,47 +36,7 @@ It achieves the following results on the evaluation set:
|
|
36 |
- Loss: 0.3121
|
37 |
- Wer: 14.5174
|
38 |
|
39 |
-
## Model description
|
40 |
|
41 |
-
More information needed
|
42 |
-
|
43 |
-
## Intended uses & limitations
|
44 |
-
|
45 |
-
More information needed
|
46 |
-
|
47 |
-
## Training and evaluation data
|
48 |
-
|
49 |
-
More information needed
|
50 |
-
|
51 |
-
## Training procedure
|
52 |
-
|
53 |
-
### Training hyperparameters
|
54 |
-
|
55 |
-
The following hyperparameters were used during training:
|
56 |
-
- learning_rate: 1e-05
|
57 |
-
- train_batch_size: 16
|
58 |
-
- eval_batch_size: 8
|
59 |
-
- seed: 42
|
60 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
-
- lr_scheduler_type: linear
|
62 |
-
- lr_scheduler_warmup_steps: 1
|
63 |
-
- training_steps: 2000
|
64 |
-
- mixed_precision_training: Native AMP
|
65 |
-
|
66 |
-
### Training results
|
67 |
-
|
68 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
-
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
70 |
-
| 0.2582 | 0.1 | 200 | 0.2807 | 15.3153 |
|
71 |
-
| 0.0882 | 1.07 | 400 | 0.2688 | 14.0541 |
|
72 |
-
| 0.0293 | 2.05 | 600 | 0.2696 | 13.5907 |
|
73 |
-
| 0.0152 | 3.02 | 800 | 0.2752 | 13.8739 |
|
74 |
-
| 0.0106 | 3.12 | 1000 | 0.2862 | 13.9511 |
|
75 |
-
| 0.0046 | 4.1 | 1200 | 0.2895 | 13.5907 |
|
76 |
-
| 0.0023 | 5.08 | 1400 | 0.3044 | 14.3372 |
|
77 |
-
| 0.0023 | 6.05 | 1600 | 0.3060 | 14.1828 |
|
78 |
-
| 0.0016 | 7.03 | 1800 | 0.3100 | 14.3887 |
|
79 |
-
| 0.0015 | 7.12 | 2000 | 0.3121 | 14.5174 |
|
80 |
|
81 |
|
82 |
### Framework versions
|
|
|
36 |
- Loss: 0.3121
|
37 |
- Wer: 14.5174
|
38 |
|
|
|
39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
|
41 |
|
42 |
### Framework versions
|