Eimhin03 commited on
Commit
42baf77
·
verified ·
1 Parent(s): 1cd615c

End of training

Browse files
Files changed (1) hide show
  1. README.md +82 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ 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: Shunya_Augmentation_enabled_attempt2
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Shunya_Augmentation_enabled_attempt2
18
+
19
+ This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.6338
22
+ - Wer: 26.8203
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0001
42
+ - train_batch_size: 2
43
+ - eval_batch_size: 4
44
+ - seed: 42
45
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 500
48
+ - training_steps: 100000
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-------:|:------:|:---------------:|:-------:|
55
+ | 0.3379 | 3.9062 | 5000 | 0.7792 | 47.4376 |
56
+ | 0.1422 | 7.8125 | 10000 | 0.7314 | 38.2661 |
57
+ | 0.1088 | 11.7188 | 15000 | 0.7569 | 38.1037 |
58
+ | 0.0704 | 15.625 | 20000 | 0.7331 | 37.7788 |
59
+ | 0.0265 | 19.5312 | 25000 | 0.7670 | 39.1670 |
60
+ | 0.0179 | 23.4375 | 30000 | 0.7927 | 36.2428 |
61
+ | 0.0225 | 27.3438 | 35000 | 0.7842 | 35.8883 |
62
+ | 0.0227 | 31.25 | 40000 | 0.7847 | 34.4705 |
63
+ | 0.0167 | 35.1562 | 45000 | 0.7585 | 32.4472 |
64
+ | 0.0149 | 39.0625 | 50000 | 0.7667 | 31.9894 |
65
+ | 0.0288 | 42.9688 | 55000 | 0.7391 | 32.6983 |
66
+ | 0.0067 | 46.875 | 60000 | 0.7365 | 31.1475 |
67
+ | 0.0048 | 50.7812 | 65000 | 0.7247 | 29.8626 |
68
+ | 0.0184 | 54.6875 | 70000 | 0.7135 | 30.5272 |
69
+ | 0.0051 | 58.5938 | 75000 | 0.7035 | 29.5525 |
70
+ | 0.0185 | 62.5 | 80000 | 0.6938 | 29.1833 |
71
+ | 0.0008 | 66.4062 | 85000 | 0.6732 | 30.0399 |
72
+ | 0.0068 | 70.3125 | 90000 | 0.6482 | 28.3710 |
73
+ | 0.0065 | 74.2188 | 95000 | 0.6310 | 27.7212 |
74
+ | 0.0001 | 78.125 | 100000 | 0.6338 | 26.8203 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 5.3.0.dev0
80
+ - Pytorch 2.9.0+cu126
81
+ - Datasets 4.0.0
82
+ - Tokenizers 0.22.2