liuh6 commited on
Commit
fd6145c
·
verified ·
1 Parent(s): 820fa70

End of training

Browse files
Files changed (2) hide show
  1. README.md +8 -7
  2. model.safetensors +1 -1
README.md CHANGED
@@ -24,7 +24,7 @@ model-index:
24
  metrics:
25
  - name: Wer
26
  type: wer
27
- value: 16.25099285146942
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
34
 
35
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Chinese English dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.3512
38
- - Wer: 16.2510
39
 
40
  ## Model description
41
 
@@ -57,18 +57,19 @@ The following hyperparameters were used during training:
57
  - learning_rate: 1e-05
58
  - train_batch_size: 2
59
  - eval_batch_size: 1
60
- - seed: 43
61
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
- - training_steps: 1000
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:------:|:----:|:---------------:|:-------:|
70
- | 0.2231 | 1.6667 | 500 | 0.3612 | 16.9976 |
71
- | 0.0141 | 3.3333 | 1000 | 0.3512 | 16.2510 |
 
72
 
73
 
74
  ### Framework versions
 
24
  metrics:
25
  - name: Wer
26
  type: wer
27
+ value: 16.64813343923749
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
34
 
35
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Chinese English dataset.
36
  It achieves the following results on the evaluation set:
37
+ - Loss: 0.3973
38
+ - Wer: 16.6481
39
 
40
  ## Model description
41
 
 
57
  - learning_rate: 1e-05
58
  - train_batch_size: 2
59
  - eval_batch_size: 1
60
+ - seed: 44
61
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
+ - training_steps: 1500
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:------:|:----:|:---------------:|:-------:|
70
+ | 0.027 | 1.6667 | 500 | 0.3876 | 16.6481 |
71
+ | 0.0046 | 3.3333 | 1000 | 0.3926 | 16.5528 |
72
+ | 0.0006 | 5.0 | 1500 | 0.3973 | 16.6481 |
73
 
74
 
75
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51f19d71615f0f4d504d85383229b2cbb8dfbf0a8a214c191f3c01443b502a08
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:861a2e50cf3ad646d26ee37e4aed5601b73a62c04aea1fda545cc58093433b5e
3
  size 151061672