Hugging Face's logo

sqrk
/
COPAS-withctrl-whisper-lg-3-Dec4

Safetensors
whisper
Generated from Trainer
Model card Files Community
sqrk commited on
Commit
69ae8f9
·
verified ·
1 Parent(s): 3f3e20f

Model save

Browse files
Files changed (3) hide show
  1. README.md +63 -7
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
README.md CHANGED
@@ -3,6 +3,8 @@ license: apache-2.0
3
  base_model: openai/whisper-large-v3
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: COPAS-withctrl-whisper-lg-3-Dec4
8
  results: []
@@ -15,13 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - eval_loss: 0.0830
19
- - eval_wer: 22.8522
20
- - eval_runtime: 180.4859
21
- - eval_samples_per_second: 0.82
22
- - eval_steps_per_second: 0.105
23
- - epoch: 63.8554
24
- - step: 5300
25
 
26
  ## Model description
27
 
@@ -52,6 +49,65 @@ The following hyperparameters were used during training:
52
  - num_epochs: 100
53
  - mixed_precision_training: Native AMP
54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  ### Framework versions
56
 
57
  - Transformers 4.43.4
 
3
  base_model: openai/whisper-large-v3
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - wer
8
  model-index:
9
  - name: COPAS-withctrl-whisper-lg-3-Dec4
10
  results: []
 
17
 
18
  This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0830
21
+ - Wer: 22.8522
 
 
 
 
 
22
 
23
  ## Model description
24
 
 
49
  - num_epochs: 100
50
  - mixed_precision_training: Native AMP
51
 
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
55
+ |:-------------:|:-------:|:----:|:---------------:|:-------:|
56
+ | 0.7468 | 1.2048 | 100 | 0.3724 | 30.8849 |
57
+ | 0.1779 | 2.4096 | 200 | 0.1806 | 26.6323 |
58
+ | 0.0631 | 3.6145 | 300 | 0.1187 | 25.4296 |
59
+ | 0.031 | 4.8193 | 400 | 0.1113 | 25.2148 |
60
+ | 0.0165 | 6.0241 | 500 | 0.0997 | 25.0 |
61
+ | 0.0104 | 7.2289 | 600 | 0.1012 | 23.7328 |
62
+ | 0.0062 | 8.4337 | 700 | 0.1017 | 25.3651 |
63
+ | 0.0053 | 9.6386 | 800 | 0.0928 | 24.0979 |
64
+ | 0.0051 | 10.8434 | 900 | 0.0956 | 24.9356 |
65
+ | 0.004 | 12.0482 | 1000 | 0.0868 | 23.3462 |
66
+ | 0.0018 | 13.2530 | 1100 | 0.0907 | 23.9905 |
67
+ | 0.0022 | 14.4578 | 1200 | 0.0915 | 23.3247 |
68
+ | 0.0025 | 15.6627 | 1300 | 0.0871 | 23.1744 |
69
+ | 0.0029 | 16.8675 | 1400 | 0.0930 | 23.8832 |
70
+ | 0.0025 | 18.0723 | 1500 | 0.0909 | 23.8617 |
71
+ | 0.0029 | 19.2771 | 1600 | 0.0818 | 23.0455 |
72
+ | 0.0027 | 20.4819 | 1700 | 0.0984 | 24.1409 |
73
+ | 0.0015 | 21.6867 | 1800 | 0.0904 | 23.8832 |
74
+ | 0.0009 | 22.8916 | 1900 | 0.0933 | 23.5610 |
75
+ | 0.0013 | 24.0964 | 2000 | 0.0917 | 23.9261 |
76
+ | 0.0016 | 25.3012 | 2100 | 0.0881 | 23.7758 |
77
+ | 0.0037 | 26.5060 | 2200 | 0.0983 | 24.4416 |
78
+ | 0.0039 | 27.7108 | 2300 | 0.1022 | 25.0215 |
79
+ | 0.0027 | 28.9157 | 2400 | 0.0839 | 23.4536 |
80
+ | 0.0032 | 30.1205 | 2500 | 0.0768 | 23.8617 |
81
+ | 0.0012 | 31.3253 | 2600 | 0.0810 | 24.8497 |
82
+ | 0.0006 | 32.5301 | 2700 | 0.0809 | 24.8926 |
83
+ | 0.0012 | 33.7349 | 2800 | 0.0738 | 23.7543 |
84
+ | 0.0012 | 34.9398 | 2900 | 0.0730 | 23.8187 |
85
+ | 0.0015 | 36.1446 | 3000 | 0.0793 | 23.5180 |
86
+ | 0.0015 | 37.3494 | 3100 | 0.0813 | 23.9046 |
87
+ | 0.0008 | 38.5542 | 3200 | 0.0784 | 23.2603 |
88
+ | 0.0006 | 39.7590 | 3300 | 0.0844 | 22.9596 |
89
+ | 0.0006 | 40.9639 | 3400 | 0.0798 | 21.9502 |
90
+ | 0.0004 | 42.1687 | 3500 | 0.0785 | 22.4442 |
91
+ | 0.0001 | 43.3735 | 3600 | 0.0792 | 22.6589 |
92
+ | 0.0 | 44.5783 | 3700 | 0.0795 | 22.0361 |
93
+ | 0.0 | 45.7831 | 3800 | 0.0799 | 22.5515 |
94
+ | 0.0 | 46.9880 | 3900 | 0.0803 | 23.0026 |
95
+ | 0.0 | 48.1928 | 4000 | 0.0807 | 23.2388 |
96
+ | 0.0 | 49.3976 | 4100 | 0.0809 | 23.1100 |
97
+ | 0.0 | 50.6024 | 4200 | 0.0812 | 22.9381 |
98
+ | 0.0 | 51.8072 | 4300 | 0.0815 | 22.9381 |
99
+ | 0.0 | 53.0120 | 4400 | 0.0816 | 22.9381 |
100
+ | 0.0 | 54.2169 | 4500 | 0.0818 | 23.0241 |
101
+ | 0.0 | 55.4217 | 4600 | 0.0820 | 23.0241 |
102
+ | 0.0 | 56.6265 | 4700 | 0.0822 | 22.8308 |
103
+ | 0.0 | 57.8313 | 4800 | 0.0823 | 22.8952 |
104
+ | 0.0 | 59.0361 | 4900 | 0.0825 | 22.8737 |
105
+ | 0.0 | 60.2410 | 5000 | 0.0826 | 22.8952 |
106
+ | 0.0 | 61.4458 | 5100 | 0.0827 | 22.8522 |
107
+ | 0.0 | 62.6506 | 5200 | 0.0829 | 22.8522 |
108
+ | 0.0 | 63.8554 | 5300 | 0.0830 | 22.8522 |
109
+
110
+
111
  ### Framework versions
112
 
113
  - Transformers 4.43.4
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a7d99c6f8c581608007874bf5e0a4d59a6128225fc3760b4831062b064f8a81
3
  size 4993448880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc7b9f5bd37877d3099b56a158f72086c53986ae7ef3cff3a218af5c25baaba
3
  size 4993448880
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ff56e060514ef2c4dafdeac6582ce5253f3a1a654af4df8b493c942a752f4aa
3
  size 1180663192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0eb5dd46bb424a56bbb94365b6ecbdb0cc66c4b61b736cb46aea2fa1175fb79
3
  size 1180663192