update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- wer
|
7 |
+
model-index:
|
8 |
+
- name: torgo_xlsr_finetune-F03-2
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# torgo_xlsr_finetune-F03-2
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.5454
|
20 |
+
- Wer: 0.8555
|
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 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_steps: 1000
|
46 |
+
- num_epochs: 30
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
52 |
+
| 25.1806 | 0.97 | 500 | 3.3512 | 1.0 |
|
53 |
+
| 3.3648 | 1.94 | 1000 | 3.1566 | 1.0 |
|
54 |
+
| 2.9865 | 2.91 | 1500 | 2.8249 | 1.0 |
|
55 |
+
| 2.8219 | 3.88 | 2000 | 2.7880 | 1.0 |
|
56 |
+
| 2.62 | 4.85 | 2500 | 2.4134 | 1.1793 |
|
57 |
+
| 2.0129 | 5.83 | 3000 | 1.7735 | 1.3777 |
|
58 |
+
| 1.3439 | 6.8 | 3500 | 1.4148 | 1.3656 |
|
59 |
+
| 0.9587 | 7.77 | 4000 | 1.3914 | 1.2437 |
|
60 |
+
| 0.7532 | 8.74 | 4500 | 1.2565 | 1.2957 |
|
61 |
+
| 0.6204 | 9.71 | 5000 | 1.2621 | 1.1074 |
|
62 |
+
| 0.5367 | 10.68 | 5500 | 1.3255 | 1.1199 |
|
63 |
+
| 0.4471 | 11.65 | 6000 | 1.2730 | 1.0789 |
|
64 |
+
| 0.3989 | 12.62 | 6500 | 1.2627 | 1.0258 |
|
65 |
+
| 0.3562 | 13.59 | 7000 | 1.3006 | 0.9754 |
|
66 |
+
| 0.3346 | 14.56 | 7500 | 1.2739 | 0.9598 |
|
67 |
+
| 0.2949 | 15.53 | 8000 | 1.3260 | 0.9238 |
|
68 |
+
| 0.2816 | 16.5 | 8500 | 1.3446 | 0.9152 |
|
69 |
+
| 0.2552 | 17.48 | 9000 | 1.3537 | 0.8848 |
|
70 |
+
| 0.2434 | 18.45 | 9500 | 1.3288 | 0.9258 |
|
71 |
+
| 0.2156 | 19.42 | 10000 | 1.3863 | 0.8812 |
|
72 |
+
| 0.2126 | 20.39 | 10500 | 1.3466 | 0.8867 |
|
73 |
+
| 0.1939 | 21.36 | 11000 | 1.4522 | 0.9113 |
|
74 |
+
| 0.1829 | 22.33 | 11500 | 1.5253 | 0.8922 |
|
75 |
+
| 0.179 | 23.3 | 12000 | 1.4589 | 0.8543 |
|
76 |
+
| 0.1684 | 24.27 | 12500 | 1.5436 | 0.8664 |
|
77 |
+
| 0.1516 | 25.24 | 13000 | 1.5324 | 0.8668 |
|
78 |
+
| 0.1472 | 26.21 | 13500 | 1.5561 | 0.8711 |
|
79 |
+
| 0.1399 | 27.18 | 14000 | 1.5400 | 0.8605 |
|
80 |
+
| 0.1405 | 28.16 | 14500 | 1.5626 | 0.8512 |
|
81 |
+
| 0.1349 | 29.13 | 15000 | 1.5454 | 0.8555 |
|
82 |
+
|
83 |
+
|
84 |
+
### Framework versions
|
85 |
+
|
86 |
+
- Transformers 4.26.1
|
87 |
+
- Pytorch 1.13.1+cu116
|
88 |
+
- Datasets 1.18.3
|
89 |
+
- Tokenizers 0.13.2
|