dongim04 commited on
Commit
5cacb1f
·
verified ·
1 Parent(s): 802f1a1

End of training

Browse files
README.md CHANGED
@@ -4,8 +4,6 @@ license: apache-2.0
4
  base_model: openai/whisper-base
5
  tags:
6
  - generated_from_trainer
7
- metrics:
8
- - wer
9
  model-index:
10
  - name: whisper-base-zh
11
  results: []
@@ -18,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.3426
22
- - Wer: 78.6221
23
 
24
  ## Model description
25
 
@@ -50,22 +48,31 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Wer |
54
- |:-------------:|:------:|:----:|:---------------:|:-------:|
55
- | 0.4992 | 0.2075 | 100 | 0.4841 | 93.0091 |
56
- | 0.4325 | 0.4149 | 200 | 0.4223 | 82.7761 |
57
- | 0.4028 | 0.6224 | 300 | 0.3979 | 81.6616 |
58
- | 0.3866 | 0.8299 | 400 | 0.3846 | 79.8886 |
59
- | 0.3322 | 1.0373 | 500 | 0.3731 | 80.3951 |
60
- | 0.3108 | 1.2448 | 600 | 0.3672 | 79.2300 |
61
- | 0.3139 | 1.4523 | 700 | 0.3601 | 79.1287 |
62
- | 0.324 | 1.6598 | 800 | 0.3558 | 78.7741 |
63
- | 0.2629 | 1.8672 | 900 | 0.3525 | 78.1155 |
64
- | 0.2421 | 2.0747 | 1000 | 0.3521 | 78.5208 |
65
- | 0.217 | 2.2822 | 1100 | 0.3495 | 78.3688 |
66
- | 0.2071 | 2.4896 | 1200 | 0.3490 | 78.5714 |
67
- | 0.2183 | 2.6971 | 1300 | 0.3452 | 78.6727 |
68
- | 0.2158 | 2.9046 | 1400 | 0.3426 | 78.6221 |
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
 
4
  base_model: openai/whisper-base
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: whisper-base-zh
9
  results: []
 
16
 
17
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.3717
20
+ - Cer: 15.8574
21
 
22
  ## Model description
23
 
 
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
53
+ | 0.5054 | 0.25 | 100 | 0.4976 | 21.1112 |
54
+ | 0.4526 | 0.5 | 200 | 0.4336 | 18.1724 |
55
+ | 0.4131 | 0.75 | 300 | 0.4105 | 20.9577 |
56
+ | 0.3772 | 1.0 | 400 | 0.3952 | 17.7166 |
57
+ | 0.297 | 1.25 | 500 | 0.3872 | 17.8054 |
58
+ | 0.2837 | 1.5 | 600 | 0.3798 | 18.3740 |
59
+ | 0.2801 | 1.75 | 700 | 0.3747 | 15.5887 |
60
+ | 0.2776 | 2.0 | 800 | 0.3677 | 16.4739 |
61
+ | 0.1981 | 2.25 | 900 | 0.3697 | 17.1169 |
62
+ | 0.2198 | 2.5 | 1000 | 0.3662 | 16.7474 |
63
+ | 0.2133 | 2.75 | 1100 | 0.3624 | 15.8334 |
64
+ | 0.2015 | 3.0 | 1200 | 0.3597 | 15.9798 |
65
+ | 0.1597 | 3.25 | 1300 | 0.3633 | 15.7902 |
66
+ | 0.1796 | 3.5 | 1400 | 0.3611 | 16.7834 |
67
+ | 0.145 | 3.75 | 1500 | 0.3607 | 16.6947 |
68
+ | 0.1581 | 4.0 | 1600 | 0.3602 | 16.2005 |
69
+ | 0.1235 | 4.25 | 1700 | 0.3639 | 14.9530 |
70
+ | 0.1118 | 4.5 | 1800 | 0.3674 | 15.3344 |
71
+ | 0.1266 | 4.75 | 1900 | 0.3654 | 15.3728 |
72
+ | 0.1214 | 5.0 | 2000 | 0.3644 | 15.3248 |
73
+ | 0.0911 | 5.25 | 2100 | 0.3678 | 15.8238 |
74
+ | 0.0969 | 5.5 | 2200 | 0.3703 | 15.8046 |
75
+ | 0.0956 | 5.75 | 2300 | 0.3717 | 15.8574 |
76
 
77
 
78
  ### Framework versions
runs/Nov19_05-10-51_bed12d1fbe20/events.out.tfevents.1731993054.bed12d1fbe20.455.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc0ad34cc10be73f7496be9afcce6d324076a3a11735648c2c242cf4ec8aa1cd
3
- size 29116
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aedc1ac15391e307e49ee67c402caa669357231b403ac72e4804b234e8e65082
3
+ size 32956