Hugging Face's logo

jlvdoorn
/
whisper-large-v2-atco2-asr-atcosim

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
1
Jan van Doorn commited on
Commit
2ba028e
·
1 Parent(s): b9e4f75

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +113 -0
README.md ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: whisper-large-v2-atco2-asr-atcosim
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # whisper-large-v2-atco2-asr-atcosim
16
+
17
+ This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.1063
20
+ - Wer: 5.5528
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 1e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 4
45
+ - total_train_batch_size: 64
46
+ - total_eval_batch_size: 32
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 250
50
+ - training_steps: 12644
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
56
+ | 0.0503 | 1.97 | 250 | 0.0602 | 8.5346 |
57
+ | 0.0172 | 3.94 | 500 | 0.0602 | 4.1352 |
58
+ | 0.0084 | 5.91 | 750 | 0.0608 | 3.3803 |
59
+ | 0.0046 | 7.87 | 1000 | 0.0624 | 3.5523 |
60
+ | 0.0024 | 9.84 | 1250 | 0.0635 | 3.5774 |
61
+ | 0.0019 | 11.81 | 1500 | 0.0704 | 4.0933 |
62
+ | 0.0019 | 13.78 | 1750 | 0.0712 | 6.3832 |
63
+ | 0.0026 | 15.75 | 2000 | 0.0677 | 3.3635 |
64
+ | 0.0016 | 17.72 | 2250 | 0.0706 | 3.2000 |
65
+ | 0.0009 | 19.69 | 2500 | 0.0709 | 4.0597 |
66
+ | 0.0003 | 21.65 | 2750 | 0.0735 | 3.2922 |
67
+ | 0.0001 | 23.62 | 3000 | 0.0771 | 3.8836 |
68
+ | 0.0001 | 25.59 | 3250 | 0.0791 | 4.0178 |
69
+ | 0.0001 | 27.56 | 3500 | 0.0804 | 3.7913 |
70
+ | 0.0002 | 29.53 | 3750 | 0.0792 | 4.0597 |
71
+ | 0.0 | 31.5 | 4000 | 0.0831 | 4.1059 |
72
+ | 0.0 | 33.46 | 4250 | 0.0847 | 3.9507 |
73
+ | 0.0 | 35.43 | 4500 | 0.0859 | 4.1059 |
74
+ | 0.0 | 37.4 | 4750 | 0.0871 | 4.1688 |
75
+ | 0.0 | 39.37 | 5000 | 0.0883 | 4.2820 |
76
+ | 0.0 | 41.34 | 5250 | 0.0891 | 4.3449 |
77
+ | 0.0 | 43.31 | 5500 | 0.0898 | 4.5378 |
78
+ | 0.0 | 45.28 | 5750 | 0.0908 | 4.5546 |
79
+ | 0.0 | 47.24 | 6000 | 0.0915 | 4.7433 |
80
+ | 0.0 | 49.21 | 6250 | 0.0923 | 4.7643 |
81
+ | 0.0 | 51.18 | 6500 | 0.0933 | 4.8146 |
82
+ | 0.0 | 53.15 | 6750 | 0.0939 | 4.7140 |
83
+ | 0.0 | 55.12 | 7000 | 0.0947 | 4.7475 |
84
+ | 0.0 | 57.09 | 7250 | 0.0955 | 4.7266 |
85
+ | 0.0 | 59.06 | 7500 | 0.0962 | 4.8188 |
86
+ | 0.0 | 61.02 | 7750 | 0.0969 | 4.8775 |
87
+ | 0.0 | 62.99 | 8000 | 0.0976 | 5.0159 |
88
+ | 0.0 | 64.96 | 8250 | 0.0982 | 5.0872 |
89
+ | 0.0 | 66.93 | 8500 | 0.0989 | 5.1669 |
90
+ | 0.0 | 68.9 | 8750 | 0.0996 | 5.1208 |
91
+ | 0.0 | 70.87 | 9000 | 0.1002 | 5.1795 |
92
+ | 0.0 | 72.83 | 9250 | 0.1009 | 5.2969 |
93
+ | 0.0 | 74.8 | 9500 | 0.1014 | 5.2969 |
94
+ | 0.0 | 76.77 | 9750 | 0.1020 | 5.3892 |
95
+ | 0.0 | 78.74 | 10000 | 0.1027 | 5.4269 |
96
+ | 0.0 | 80.71 | 10250 | 0.1031 | 5.3431 |
97
+ | 0.0 | 82.68 | 10500 | 0.1038 | 5.4479 |
98
+ | 0.0 | 84.65 | 10750 | 0.1043 | 5.4940 |
99
+ | 0.0 | 86.61 | 11000 | 0.1047 | 5.4563 |
100
+ | 0.0 | 88.58 | 11250 | 0.1052 | 5.4857 |
101
+ | 0.0 | 90.55 | 11500 | 0.1055 | 5.4857 |
102
+ | 0.0 | 92.52 | 11750 | 0.1058 | 5.5024 |
103
+ | 0.0 | 94.49 | 12000 | 0.1060 | 5.5108 |
104
+ | 0.0 | 96.46 | 12250 | 0.1062 | 5.5150 |
105
+ | 0.0 | 98.43 | 12500 | 0.1063 | 5.5528 |
106
+
107
+
108
+ ### Framework versions
109
+
110
+ - Transformers 4.30.0.dev0
111
+ - Pytorch 2.0.1+cu117
112
+ - Datasets 2.12.0
113
+ - Tokenizers 0.13.3