Hugging Face's logo

adityarra07
/
whisper-med-LoRA_FAA_data_small

Generated from Trainer
Model card Files Community
adityarra07 commited on
Commit
928bc00
•
1 Parent(s): bd1dd08

./Hugging-face-models/whisper-med-LoRA_FAA_data_small

Browse files
Files changed (2) hide show
  1. README.md +14 -9
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 4.2316
21
  - Wer: 56.9444
22
 
23
  ## Model description
@@ -38,22 +38,27 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 1e-05
41
- - train_batch_size: 16
42
- - eval_batch_size: 16
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 5
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Wer |
51
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
52
- | 4.5172 | 1.0 | 2 | 4.4875 | 56.9444 |
53
- | 4.3742 | 2.0 | 4 | 4.4471 | 56.9444 |
54
- | 4.5366 | 3.0 | 6 | 4.3552 | 56.9444 |
55
- | 4.3537 | 4.0 | 8 | 4.3168 | 56.9444 |
56
- | 4.1782 | 5.0 | 10 | 4.2316 | 56.9444 |
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 4.4632
21
  - Wer: 56.9444
22
 
23
  ## Model description
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 1e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 10
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Wer |
51
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
52
+ | 4.4359 | 1.0 | 1 | 4.5014 | 56.9444 |
53
+ | 4.4359 | 2.0 | 2 | 4.5014 | 56.9444 |
54
+ | 4.4359 | 3.0 | 3 | 4.5496 | 56.9444 |
55
+ | 4.458 | 4.0 | 4 | 4.5496 | 56.9444 |
56
+ | 4.4576 | 5.0 | 5 | 4.5439 | 56.9444 |
57
+ | 4.4411 | 6.0 | 6 | 4.4745 | 56.9444 |
58
+ | 4.4139 | 7.0 | 7 | 4.4745 | 56.9444 |
59
+ | 4.4166 | 8.0 | 8 | 4.4745 | 56.9444 |
60
+ | 4.4181 | 9.0 | 9 | 4.4722 | 56.9444 |
61
+ | 4.379 | 10.0 | 10 | 4.4632 | 56.9444 |
62
 
63
 
64
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffdf3a55a01e9fd4af660072ebac4e4819eb466de7879d194ac9fba96fe29e06
3
  size 75604173
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cd8e8a1a5af9e52a2ebbc7b0170a25bb522fa466d8ec4a6a12556dae0bf4c80
3
  size 75604173