update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- wer
|
6 |
+
model-index:
|
7 |
+
- name: hubert-base-libri-pruning-v2-testing4
|
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 |
+
# hubert-base-libri-pruning-v2-testing4
|
15 |
+
|
16 |
+
This model was trained from scratch on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: -7567.2393
|
19 |
+
- Wer: 0.4152
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.00015
|
39 |
+
- train_batch_size: 64
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 3000
|
45 |
+
- num_epochs: 30
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
52 |
+
| -14.3764 | 1.12 | 500 | -47.0110 | 0.5199 |
|
53 |
+
| -106.5551 | 2.24 | 1000 | -189.6375 | 0.4788 |
|
54 |
+
| -290.9837 | 3.36 | 1500 | -427.6701 | 0.4637 |
|
55 |
+
| -566.8718 | 4.48 | 2000 | -760.7963 | 0.4523 |
|
56 |
+
| -932.8283 | 5.61 | 2500 | -1188.8673 | 0.4457 |
|
57 |
+
| -1393.9495 | 6.73 | 3000 | -1711.7064 | 0.4362 |
|
58 |
+
| -1926.4679 | 7.85 | 3500 | -2267.1279 | 0.4336 |
|
59 |
+
| -2446.4408 | 8.97 | 4000 | -2795.6897 | 0.4307 |
|
60 |
+
| -2944.8128 | 10.09 | 4500 | -3294.3000 | 0.4279 |
|
61 |
+
| -3416.905 | 11.21 | 5000 | -3766.8943 | 0.4254 |
|
62 |
+
| -3865.4817 | 12.33 | 5500 | -4211.6885 | 0.4219 |
|
63 |
+
| -4285.8215 | 13.45 | 6000 | -4628.7329 | 0.4223 |
|
64 |
+
| -4660.695 | 14.57 | 6500 | -5017.9912 | 0.4184 |
|
65 |
+
| -5032.002 | 15.7 | 7000 | -5379.4785 | 0.4213 |
|
66 |
+
| -5351.629 | 16.82 | 7500 | -5713.4419 | 0.4186 |
|
67 |
+
| -5659.1765 | 17.94 | 8000 | -6019.7510 | 0.4195 |
|
68 |
+
| -5957.58 | 19.06 | 8500 | -6296.5054 | 0.4189 |
|
69 |
+
| -6215.3305 | 20.18 | 9000 | -6547.0381 | 0.4165 |
|
70 |
+
| -6441.2955 | 21.3 | 9500 | -6770.7163 | 0.4172 |
|
71 |
+
| -6651.3045 | 22.42 | 10000 | -6966.9087 | 0.4160 |
|
72 |
+
| -6811.32 | 23.54 | 10500 | -7135.6860 | 0.4155 |
|
73 |
+
| -6964.2775 | 24.66 | 11000 | -7277.1060 | 0.4171 |
|
74 |
+
| -7115.7955 | 25.78 | 11500 | -7390.9673 | 0.4156 |
|
75 |
+
| -7187.0235 | 26.91 | 12000 | -7477.7656 | 0.4151 |
|
76 |
+
| -7259.9035 | 28.03 | 12500 | -7535.0112 | 0.4148 |
|
77 |
+
| -7302.289 | 29.15 | 13000 | -7567.2393 | 0.4152 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.30.0.dev0
|
83 |
+
- Pytorch 2.0.1
|
84 |
+
- Datasets 2.12.1.dev0
|
85 |
+
- Tokenizers 0.13.3
|