Hugging Face's logo

dongim04
/
whisper-base-en

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
dongim04 commited on
Commit
abcec86
•
1 Parent(s): d799de4

End of training

Browse files
Files changed (2) hide show
  1. README.md +29 -18
  2. runs/Nov19_09-19-10_53be0e62afda/events.out.tfevents.1732007957.53be0e62afda.1551.3 +2 -2
README.md CHANGED
@@ -18,8 +18,8 @@ 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: 0.1362
22
- - Wer: 4.3516
23
 
24
  ## Model description
25
 
@@ -38,7 +38,7 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 5e-06
42
  - train_batch_size: 8
43
  - eval_batch_size: 16
44
  - seed: 42
@@ -46,26 +46,37 @@ The following hyperparameters were used during training:
46
  - total_train_batch_size: 16
47
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
- - lr_scheduler_warmup_steps: 50
50
  - training_steps: 3000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Wer |
56
- |:-------------:|:-----:|:----:|:---------------:|:------:|
57
- | 0.0146 | 0.4 | 100 | 0.1223 | 4.8708 |
58
- | 0.0159 | 0.8 | 200 | 0.1248 | 4.8306 |
59
- | 0.0104 | 1.2 | 300 | 0.1251 | 4.3803 |
60
- | 0.01 | 1.6 | 400 | 0.1259 | 4.3975 |
61
- | 0.0092 | 2.0 | 500 | 0.1263 | 4.4749 |
62
- | 0.0055 | 2.4 | 600 | 0.1301 | 4.3344 |
63
- | 0.0062 | 2.8 | 700 | 0.1303 | 4.4061 |
64
- | 0.0039 | 3.2 | 800 | 0.1324 | 4.5294 |
65
- | 0.0045 | 3.6 | 900 | 0.1337 | 4.3889 |
66
- | 0.0036 | 4.0 | 1000 | 0.1350 | 4.2626 |
67
- | 0.0033 | 4.4 | 1100 | 0.1358 | 4.3344 |
68
- | 0.0033 | 4.8 | 1200 | 0.1362 | 4.3516 |
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
 
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: 0.1334
22
+ - Wer: 6.9935
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 1e-06
42
  - train_batch_size: 8
43
  - eval_batch_size: 16
44
  - seed: 42
 
46
  - total_train_batch_size: 16
47
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
 
49
  - training_steps: 3000
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
55
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
56
+ | 0.5784 | 0.4 | 100 | 0.3881 | 20.8915 |
57
+ | 0.2412 | 0.8 | 200 | 0.2176 | 12.1310 |
58
+ | 0.1962 | 1.2 | 300 | 0.1909 | 10.6681 |
59
+ | 0.182 | 1.6 | 400 | 0.1782 | 9.7530 |
60
+ | 0.1683 | 2.0 | 500 | 0.1697 | 8.9785 |
61
+ | 0.1418 | 2.4 | 600 | 0.1639 | 8.9699 |
62
+ | 0.1605 | 2.8 | 700 | 0.1590 | 8.4593 |
63
+ | 0.13 | 3.2 | 800 | 0.1550 | 7.9774 |
64
+ | 0.1353 | 3.6 | 900 | 0.1518 | 7.7623 |
65
+ | 0.13 | 4.0 | 1000 | 0.1491 | 7.4897 |
66
+ | 0.1288 | 4.4 | 1100 | 0.1467 | 7.4897 |
67
+ | 0.12 | 4.8 | 1200 | 0.1448 | 7.4180 |
68
+ | 0.1161 | 5.2 | 1300 | 0.1428 | 7.3807 |
69
+ | 0.113 | 5.6 | 1400 | 0.1414 | 7.5356 |
70
+ | 0.1022 | 6.0 | 1500 | 0.1399 | 6.9505 |
71
+ | 0.1029 | 6.4 | 1600 | 0.1390 | 6.9361 |
72
+ | 0.0981 | 6.8 | 1700 | 0.1379 | 6.8070 |
73
+ | 0.1051 | 7.2 | 1800 | 0.1369 | 6.8357 |
74
+ | 0.0927 | 7.6 | 1900 | 0.1362 | 6.8988 |
75
+ | 0.0973 | 8.0 | 2000 | 0.1354 | 6.8042 |
76
+ | 0.0898 | 8.4 | 2100 | 0.1348 | 6.7497 |
77
+ | 0.0929 | 8.8 | 2200 | 0.1342 | 6.7870 |
78
+ | 0.0937 | 9.2 | 2300 | 0.1338 | 7.0623 |
79
+ | 0.0901 | 9.6 | 2400 | 0.1334 | 6.9935 |
80
 
81
 
82
  ### Framework versions
runs/Nov19_09-19-10_53be0e62afda/events.out.tfevents.1732007957.53be0e62afda.1551.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5aaad1c9ac94995acdb940f1081e52c92bdb385c692b7f4bd42f67085db6e8c
3
- size 20685
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:427c67ddbff68afeba6a7c7c15d08ebb62fcc8a6619c44f556faa33bc8744a64
3
+ size 23999