update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: ai-light-dance_chord_ft_wav2vec2-large-xlsr-53
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# ai-light-dance_chord_ft_wav2vec2-large-xlsr-53
|
14 |
+
|
15 |
+
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.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.9477
|
18 |
+
- Wer: 0.9781
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 3e-05
|
38 |
+
- train_batch_size: 10
|
39 |
+
- eval_batch_size: 10
|
40 |
+
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 16
|
42 |
+
- total_train_batch_size: 160
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- lr_scheduler_warmup_steps: 100
|
46 |
+
- num_epochs: 50.0
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
53 |
+
| 5.1857 | 1.0 | 126 | 4.5913 | 1.0 |
|
54 |
+
| 3.0939 | 2.0 | 252 | 3.0160 | 1.0 |
|
55 |
+
| 2.8403 | 3.0 | 378 | 2.7337 | 1.0 |
|
56 |
+
| 2.2525 | 4.0 | 504 | 2.5588 | 0.9825 |
|
57 |
+
| 2.0291 | 5.0 | 630 | 2.5216 | 0.9701 |
|
58 |
+
| 1.9083 | 6.0 | 756 | 2.3990 | 0.9514 |
|
59 |
+
| 1.8745 | 7.0 | 882 | 2.2781 | 0.9474 |
|
60 |
+
| 1.8222 | 8.0 | 1008 | 2.2360 | 0.9471 |
|
61 |
+
| 1.7871 | 9.0 | 1134 | 2.1960 | 0.9463 |
|
62 |
+
| 1.7225 | 10.0 | 1260 | 2.0775 | 0.9464 |
|
63 |
+
| 1.6856 | 11.0 | 1386 | 2.0817 | 0.9518 |
|
64 |
+
| 1.6903 | 12.0 | 1512 | 2.0607 | 0.9534 |
|
65 |
+
| 1.6034 | 13.0 | 1638 | 1.9956 | 0.9504 |
|
66 |
+
| 1.6171 | 14.0 | 1764 | 2.0099 | 0.9490 |
|
67 |
+
| 1.5508 | 15.0 | 1890 | 2.0424 | 0.9591 |
|
68 |
+
| 1.539 | 16.0 | 2016 | 1.9728 | 0.9600 |
|
69 |
+
| 1.5176 | 17.0 | 2142 | 2.0421 | 0.9628 |
|
70 |
+
| 1.5088 | 18.0 | 2268 | 1.9428 | 0.9598 |
|
71 |
+
| 1.4739 | 19.0 | 2394 | 1.9886 | 0.9591 |
|
72 |
+
| 1.4228 | 20.0 | 2520 | 2.0164 | 0.9670 |
|
73 |
+
| 1.4277 | 21.0 | 2646 | 1.9968 | 0.9704 |
|
74 |
+
| 1.3834 | 22.0 | 2772 | 1.9882 | 0.9669 |
|
75 |
+
| 1.3768 | 23.0 | 2898 | 1.9519 | 0.9606 |
|
76 |
+
| 1.3747 | 24.0 | 3024 | 1.8923 | 0.9580 |
|
77 |
+
| 1.3533 | 25.0 | 3150 | 1.9767 | 0.9707 |
|
78 |
+
| 1.3312 | 26.0 | 3276 | 1.8993 | 0.9609 |
|
79 |
+
| 1.2743 | 27.0 | 3402 | 1.9494 | 0.9705 |
|
80 |
+
| 1.2924 | 28.0 | 3528 | 1.9019 | 0.9631 |
|
81 |
+
| 1.2621 | 29.0 | 3654 | 1.9110 | 0.9596 |
|
82 |
+
| 1.2387 | 30.0 | 3780 | 1.9118 | 0.9627 |
|
83 |
+
| 1.228 | 31.0 | 3906 | 1.8722 | 0.9590 |
|
84 |
+
| 1.1938 | 32.0 | 4032 | 1.8890 | 0.9599 |
|
85 |
+
| 1.1887 | 33.0 | 4158 | 1.9175 | 0.9653 |
|
86 |
+
| 1.1807 | 34.0 | 4284 | 1.8983 | 0.9649 |
|
87 |
+
| 1.1553 | 35.0 | 4410 | 1.9246 | 0.9703 |
|
88 |
+
| 1.1448 | 36.0 | 4536 | 1.9248 | 0.9705 |
|
89 |
+
| 1.1146 | 37.0 | 4662 | 1.9747 | 0.9804 |
|
90 |
+
| 1.1394 | 38.0 | 4788 | 1.9119 | 0.9723 |
|
91 |
+
| 1.1206 | 39.0 | 4914 | 1.8931 | 0.9630 |
|
92 |
+
| 1.0892 | 40.0 | 5040 | 1.9243 | 0.9668 |
|
93 |
+
| 1.104 | 41.0 | 5166 | 1.8965 | 0.9671 |
|
94 |
+
| 1.054 | 42.0 | 5292 | 1.9477 | 0.9755 |
|
95 |
+
| 1.0922 | 43.0 | 5418 | 1.8969 | 0.9699 |
|
96 |
+
| 1.0484 | 44.0 | 5544 | 1.9423 | 0.9733 |
|
97 |
+
| 1.0567 | 45.0 | 5670 | 1.9412 | 0.9745 |
|
98 |
+
| 1.0615 | 46.0 | 5796 | 1.9076 | 0.9674 |
|
99 |
+
| 1.0201 | 47.0 | 5922 | 1.9384 | 0.9743 |
|
100 |
+
| 1.0664 | 48.0 | 6048 | 1.9509 | 0.9816 |
|
101 |
+
| 1.0498 | 49.0 | 6174 | 1.9426 | 0.9757 |
|
102 |
+
| 1.0303 | 50.0 | 6300 | 1.9477 | 0.9781 |
|
103 |
+
|
104 |
+
|
105 |
+
### Framework versions
|
106 |
+
|
107 |
+
- Transformers 4.21.0.dev0
|
108 |
+
- Pytorch 1.9.1+cu102
|
109 |
+
- Datasets 2.3.3.dev0
|
110 |
+
- Tokenizers 0.12.1
|