Hugging Face's logo

haseong8012
/
wav2vec2-large-xlsr-53_ko2

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Community
haseong8012 commited on
Commit
ab5a948
•
1 Parent(s): 3657eca

End of training

Browse files
Files changed (2) hide show
  1. README.md +127 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-large-xlsr-53
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - zeroth_korean
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: wav2vec2-large-xlsr-53-fine-tune_korean_byAILAB2
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: zeroth_korean
18
+ type: zeroth_korean
19
+ config: clean
20
+ split: test
21
+ args: clean
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.9067911459117602
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # wav2vec2-large-xlsr-53-fine-tune_korean_byAILAB2
32
+
33
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the zeroth_korean dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.4929
36
+ - Wer: 0.9068
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 0.0002
56
+ - train_batch_size: 16
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 2
60
+ - total_train_batch_size: 32
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_steps: 500
64
+ - num_epochs: 50
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
69
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | No log | 0.99 | 38 | 54.4059 | 1.0 |
71
+ | No log | 2.0 | 77 | 38.8388 | 1.0 |
72
+ | No log | 2.99 | 115 | 24.1740 | 1.0 |
73
+ | No log | 4.0 | 154 | 16.4733 | 1.0 |
74
+ | No log | 4.99 | 192 | 10.1900 | 1.0 |
75
+ | No log | 6.0 | 231 | 6.0076 | 1.0 |
76
+ | No log | 6.99 | 269 | 4.8990 | 1.0 |
77
+ | No log | 8.0 | 308 | 4.8442 | 1.0 |
78
+ | No log | 8.99 | 346 | 4.8284 | 1.0 |
79
+ | No log | 10.0 | 385 | 4.8316 | 1.0 |
80
+ | 16.886 | 10.99 | 423 | 4.8164 | 1.0 |
81
+ | 16.886 | 12.0 | 462 | 4.7815 | 1.0 |
82
+ | 16.886 | 12.99 | 500 | 4.7204 | 0.9989 |
83
+ | 16.886 | 14.0 | 539 | 4.6842 | 0.9989 |
84
+ | 16.886 | 14.99 | 577 | 4.6641 | 0.9994 |
85
+ | 16.886 | 16.0 | 616 | 4.6527 | 1.0 |
86
+ | 16.886 | 16.99 | 654 | 4.6745 | 0.9992 |
87
+ | 16.886 | 18.0 | 693 | 4.6591 | 1.0 |
88
+ | 16.886 | 18.99 | 731 | 4.6506 | 0.9997 |
89
+ | 16.886 | 20.0 | 770 | 4.6719 | 0.9967 |
90
+ | 4.4391 | 20.99 | 808 | 4.6067 | 0.9968 |
91
+ | 4.4391 | 22.0 | 847 | 4.5748 | 0.9968 |
92
+ | 4.4391 | 22.99 | 885 | 4.5166 | 0.9962 |
93
+ | 4.4391 | 24.0 | 924 | 4.3783 | 0.9926 |
94
+ | 4.4391 | 24.99 | 962 | 4.2711 | 0.9913 |
95
+ | 4.4391 | 26.0 | 1001 | 3.6515 | 1.0030 |
96
+ | 4.4391 | 26.99 | 1039 | 3.1057 | 1.0640 |
97
+ | 4.4391 | 28.0 | 1078 | 2.6593 | 1.0742 |
98
+ | 4.4391 | 28.99 | 1116 | 2.4071 | 1.0587 |
99
+ | 4.4391 | 30.0 | 1155 | 2.2041 | 1.0379 |
100
+ | 4.4391 | 30.99 | 1193 | 2.0495 | 1.0319 |
101
+ | 3.1722 | 32.0 | 1232 | 1.9754 | 1.0459 |
102
+ | 3.1722 | 32.99 | 1270 | 1.8658 | 0.9968 |
103
+ | 3.1722 | 34.0 | 1309 | 1.7887 | 0.9883 |
104
+ | 3.1722 | 34.99 | 1347 | 1.7560 | 0.9776 |
105
+ | 3.1722 | 36.0 | 1386 | 1.6987 | 0.9675 |
106
+ | 3.1722 | 36.99 | 1424 | 1.6513 | 0.9443 |
107
+ | 3.1722 | 38.0 | 1463 | 1.6187 | 0.9473 |
108
+ | 3.1722 | 38.99 | 1501 | 1.6210 | 0.9408 |
109
+ | 3.1722 | 40.0 | 1540 | 1.5957 | 0.9458 |
110
+ | 3.1722 | 40.99 | 1578 | 1.5673 | 0.9246 |
111
+ | 1.2364 | 42.0 | 1617 | 1.5748 | 0.9286 |
112
+ | 1.2364 | 42.99 | 1655 | 1.5333 | 0.9217 |
113
+ | 1.2364 | 44.0 | 1694 | 1.5138 | 0.9100 |
114
+ | 1.2364 | 44.99 | 1732 | 1.5244 | 0.9223 |
115
+ | 1.2364 | 46.0 | 1771 | 1.5041 | 0.9080 |
116
+ | 1.2364 | 46.99 | 1809 | 1.5151 | 0.9155 |
117
+ | 1.2364 | 48.0 | 1848 | 1.4955 | 0.9077 |
118
+ | 1.2364 | 48.99 | 1886 | 1.4924 | 0.9065 |
119
+ | 1.2364 | 49.35 | 1900 | 1.4929 | 0.9068 |
120
+
121
+
122
+ ### Framework versions
123
+
124
+ - Transformers 4.33.2
125
+ - Pytorch 1.12.1
126
+ - Datasets 2.14.5
127
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:125e2ce5a907c5d82ca2ad6d0df8049b46b95e3a49eac30f8bfe317fee3f733b
3
  size 1266847409
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b9cf6653e89cad831360860dfffda3344a9b298cbf2626ab452e35ea1bac3d
3
  size 1266847409