scarlett623 commited on
Commit
a80129d
1 Parent(s): 32b19a3

Model save

Browse files
Files changed (2) hide show
  1. README.md +2 -57
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -1,10 +1,8 @@
1
  ---
2
  license: apache-2.0
3
- base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
5
  - generated_from_trainer
6
- metrics:
7
- - wer
8
  model-index:
9
  - name: wav2vec2-timit-xls-r-53-wandb-colab
10
  results: []
@@ -15,11 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # wav2vec2-timit-xls-r-53-wandb-colab
17
 
18
- 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.
19
- It achieves the following results on the evaluation set:
20
- - Loss: 0.2451
21
- - Wer: 0.2503
22
- - Cer: 0.0799
23
 
24
  ## Model description
25
 
@@ -47,55 +41,6 @@ The following hyperparameters were used during training:
47
  - lr_scheduler_warmup_steps: 1000
48
  - num_epochs: 30
49
 
50
- ### Training results
51
-
52
- | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
53
- |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
54
- | No log | 0.69 | 400 | 3.1514 | 1.0 | 0.9790 |
55
- | 5.094 | 1.38 | 800 | 2.8674 | 1.0 | 0.9790 |
56
- | 2.595 | 2.08 | 1200 | 0.5208 | 0.5344 | 0.1541 |
57
- | 0.8139 | 2.77 | 1600 | 0.3568 | 0.4234 | 0.1275 |
58
- | 0.4793 | 3.46 | 2000 | 0.2954 | 0.3645 | 0.1106 |
59
- | 0.4793 | 4.15 | 2400 | 0.2649 | 0.3475 | 0.1037 |
60
- | 0.3771 | 4.84 | 2800 | 0.2452 | 0.3186 | 0.0976 |
61
- | 0.2912 | 5.54 | 3200 | 0.2385 | 0.3079 | 0.0960 |
62
- | 0.2632 | 6.23 | 3600 | 0.2292 | 0.2954 | 0.0911 |
63
- | 0.2176 | 6.92 | 4000 | 0.2248 | 0.2910 | 0.0908 |
64
- | 0.2176 | 7.61 | 4400 | 0.2279 | 0.2816 | 0.0888 |
65
- | 0.1958 | 8.3 | 4800 | 0.2227 | 0.2819 | 0.0878 |
66
- | 0.1846 | 9.0 | 5200 | 0.2277 | 0.2779 | 0.0876 |
67
- | 0.1573 | 9.69 | 5600 | 0.2280 | 0.2830 | 0.0877 |
68
- | 0.1471 | 10.38 | 6000 | 0.2345 | 0.2770 | 0.0880 |
69
- | 0.1471 | 11.07 | 6400 | 0.2389 | 0.2714 | 0.0852 |
70
- | 0.133 | 11.76 | 6800 | 0.2253 | 0.2730 | 0.0869 |
71
- | 0.1317 | 12.46 | 7200 | 0.2179 | 0.2662 | 0.0846 |
72
- | 0.1268 | 13.15 | 7600 | 0.2315 | 0.2678 | 0.0851 |
73
- | 0.1147 | 13.84 | 8000 | 0.2501 | 0.2679 | 0.0849 |
74
- | 0.1147 | 14.53 | 8400 | 0.2463 | 0.2663 | 0.0839 |
75
- | 0.1151 | 15.22 | 8800 | 0.2429 | 0.2662 | 0.0848 |
76
- | 0.0968 | 15.92 | 9200 | 0.2502 | 0.2639 | 0.0839 |
77
- | 0.0985 | 16.61 | 9600 | 0.2589 | 0.2616 | 0.0838 |
78
- | 0.0938 | 17.3 | 10000 | 0.2414 | 0.2595 | 0.0835 |
79
- | 0.0938 | 17.99 | 10400 | 0.2420 | 0.2617 | 0.0839 |
80
- | 0.0878 | 18.69 | 10800 | 0.2257 | 0.2597 | 0.0829 |
81
- | 0.0872 | 19.38 | 11200 | 0.2654 | 0.2586 | 0.0825 |
82
- | 0.0774 | 20.07 | 11600 | 0.2558 | 0.2579 | 0.0829 |
83
- | 0.0743 | 20.76 | 12000 | 0.2375 | 0.2564 | 0.0824 |
84
- | 0.0743 | 21.45 | 12400 | 0.2522 | 0.2568 | 0.0813 |
85
- | 0.0832 | 22.15 | 12800 | 0.2363 | 0.2569 | 0.0817 |
86
- | 0.0698 | 22.84 | 13200 | 0.2510 | 0.2574 | 0.0816 |
87
- | 0.0677 | 23.53 | 13600 | 0.2535 | 0.2570 | 0.0818 |
88
- | 0.0648 | 24.22 | 14000 | 0.2595 | 0.2571 | 0.0819 |
89
- | 0.0648 | 24.91 | 14400 | 0.2441 | 0.2542 | 0.0815 |
90
- | 0.0685 | 25.61 | 14800 | 0.2503 | 0.2534 | 0.0803 |
91
- | 0.066 | 26.3 | 15200 | 0.2489 | 0.2533 | 0.0804 |
92
- | 0.0583 | 26.99 | 15600 | 0.2471 | 0.2512 | 0.0802 |
93
- | 0.0624 | 27.68 | 16000 | 0.2487 | 0.2516 | 0.0804 |
94
- | 0.0624 | 28.37 | 16400 | 0.2470 | 0.2518 | 0.0804 |
95
- | 0.0663 | 29.07 | 16800 | 0.2478 | 0.2510 | 0.0800 |
96
- | 0.0569 | 29.76 | 17200 | 0.2451 | 0.2503 | 0.0799 |
97
-
98
-
99
  ### Framework versions
100
 
101
  - Transformers 4.32.0.dev0
 
1
  ---
2
  license: apache-2.0
3
+ base_model: facebook/wav2vec2-xls-r-300m
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: wav2vec2-timit-xls-r-53-wandb-colab
8
  results: []
 
13
 
14
  # wav2vec2-timit-xls-r-53-wandb-colab
15
 
16
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
 
 
 
 
17
 
18
  ## Model description
19
 
 
41
  - lr_scheduler_warmup_steps: 1000
42
  - num_epochs: 30
43
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
  ### Framework versions
45
 
46
  - Transformers 4.32.0.dev0
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:769adb4e9b255d0192978323ea0c5eebc21a0f5530773a7edacf7a50bf134b93
3
  size 1262033069
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:742a4e231232f628fa745a94205835473449519c10aa0b9124aee56eb0999b18
3
  size 1262033069