Hugging Face's logo

weewtr1121
/
outs

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
weewtr1121 commited on
Commit
78f78db
•
1 Parent(s): 7adfe15

./outs

Browse files
Files changed (4) hide show
  1. README.md +24 -11
  2. model.safetensors +1 -1
  3. runs/Oct09_00-55-31_9416d025a519/events.out.tfevents.1728435341.9416d025a519.3585.1 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [biodatlab/whisper-th-medium-combined](https://huggingface.co/biodatlab/whisper-th-medium-combined) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.0790
20
- - Cer: 4.9548
21
 
22
  ## Model description
23
 
@@ -36,24 +36,37 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 1.5e-05
40
- - train_batch_size: 8
41
- - eval_batch_size: 8
42
  - seed: 42
43
- - gradient_accumulation_steps: 4
44
  - total_train_batch_size: 32
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
- - lr_scheduler_type: cosine
47
- - lr_scheduler_warmup_steps: 2000
48
- - num_epochs: 12.0
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Cer |
54
  |:-------------:|:-------:|:----:|:---------------:|:------:|
55
- | 0.0684 | 5.9480 | 400 | 0.0792 | 4.7985 |
56
- | 0.0306 | 11.8959 | 800 | 0.0790 | 4.9548 |
 
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [biodatlab/whisper-th-medium-combined](https://huggingface.co/biodatlab/whisper-th-medium-combined) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0878
20
+ - Cer: 5.4469
21
 
22
  ## Model description
23
 
 
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: 16
42
  - seed: 42
43
+ - gradient_accumulation_steps: 2
44
  - total_train_batch_size: 32
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: cosine_with_restarts
47
+ - lr_scheduler_warmup_steps: 5000
48
+ - num_epochs: 15.0
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Cer |
54
  |:-------------:|:-------:|:----:|:---------------:|:------:|
55
+ | 0.0275 | 0.9926 | 67 | 0.0804 | 4.9648 |
56
+ | 0.0359 | 2.0 | 135 | 0.0807 | 6.0688 |
57
+ | 0.0317 | 2.9926 | 202 | 0.0813 | 5.8626 |
58
+ | 0.0196 | 4.0 | 270 | 0.0819 | 4.9681 |
59
+ | 0.021 | 4.9926 | 337 | 0.0823 | 4.8683 |
60
+ | 0.0209 | 6.0 | 405 | 0.0831 | 4.8783 |
61
+ | 0.0223 | 6.9926 | 472 | 0.0866 | 5.0080 |
62
+ | 0.0173 | 8.0 | 540 | 0.0864 | 5.2541 |
63
+ | 0.0231 | 8.9926 | 607 | 0.0839 | 4.6422 |
64
+ | 0.0131 | 10.0 | 675 | 0.0860 | 5.3405 |
65
+ | 0.0134 | 10.9926 | 742 | 0.0899 | 5.2674 |
66
+ | 0.0183 | 12.0 | 810 | 0.0873 | 5.8094 |
67
+ | 0.0172 | 12.9926 | 877 | 0.0893 | 4.9215 |
68
+ | 0.0178 | 14.0 | 945 | 0.0855 | 5.7096 |
69
+ | 0.0127 | 14.8889 | 1005 | 0.0878 | 5.4469 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5850b89ece9a9f37af996094cae634da51c2d67ba542de4c481f4d4593ecda58
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc97763a10671b5ff72c55cf99893c64a22326c8e0ce738e5ecedb4fe6a48043
3
  size 3055544304
runs/Oct09_00-55-31_9416d025a519/events.out.tfevents.1728435341.9416d025a519.3585.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ee43671d9ce7fc57aa95c9957eaa76006e1bffdaa9b90eb33f0f7a31106d10d
3
+ size 15032
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:801b57d6e209b70a4192c786c9f9127b8b99b2b5d27a1c0a67d7bfed8f8bc8e0
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a0db6e5e59dd3fc0ff2bca34fa2f997522442d7699f5aba50151e0a3e668d41
3
  size 5304