update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
name: Waynehills-STT-doogie-server
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# Waynehills-STT-doogie-server
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [Doogie/Waynehills-STT-doogie](https://huggingface.co/Doogie/Waynehills-STT-doogie) on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 2.8554
|
17 |
+
- Wer: 0.9881
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.0001
|
37 |
+
- train_batch_size: 1
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- lr_scheduler_warmup_steps: 1000
|
43 |
+
- num_epochs: 20
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
48 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
49 |
+
| 4.6882 | 1.2 | 1000 | 4.8098 | 0.9970 |
|
50 |
+
| 2.4927 | 2.4 | 2000 | 2.9959 | 1.0416 |
|
51 |
+
| 1.6066 | 3.59 | 3000 | 2.5789 | 0.9442 |
|
52 |
+
| 1.2902 | 4.79 | 4000 | 2.6152 | 1.0439 |
|
53 |
+
| 1.0486 | 5.99 | 5000 | 2.5047 | 1.0861 |
|
54 |
+
| 0.8648 | 7.19 | 6000 | 2.4007 | 0.9347 |
|
55 |
+
| 0.7659 | 8.38 | 7000 | 2.5087 | 0.9602 |
|
56 |
+
| 0.6357 | 9.58 | 8000 | 2.5803 | 1.0018 |
|
57 |
+
| 0.5684 | 10.78 | 9000 | 2.6190 | 0.9656 |
|
58 |
+
| 0.5647 | 11.98 | 10000 | 2.6129 | 0.9436 |
|
59 |
+
| 0.5048 | 13.17 | 11000 | 2.7174 | 0.9816 |
|
60 |
+
| 0.4405 | 14.37 | 12000 | 2.7107 | 0.9519 |
|
61 |
+
| 0.4273 | 15.57 | 13000 | 2.7672 | 0.9673 |
|
62 |
+
| 0.4049 | 16.77 | 14000 | 2.8277 | 0.9869 |
|
63 |
+
| 0.3731 | 17.96 | 15000 | 2.8238 | 0.9786 |
|
64 |
+
| 0.3761 | 19.16 | 16000 | 2.8554 | 0.9881 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.12.5
|
70 |
+
- Pytorch 1.10.0+cu113
|
71 |
+
- Datasets 1.16.1
|
72 |
+
- Tokenizers 0.10.3
|