eai6 commited on
Commit
a995ab2
·
verified ·
1 Parent(s): 5b1e05d

End of training

Browse files
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Wer
25
  type: wer
26
- value: 211.83431952662724
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on the Nyansapo AI Dataset dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 1.8047
37
- - Wer: 211.8343
38
 
39
  ## Model description
40
 
@@ -62,16 +62,15 @@ The following hyperparameters were used during training:
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 50
65
- - training_steps: 200
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Wer |
70
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
- | 3.1416 | 5.0 | 50 | 2.3270 | 56.2130 |
72
- | 1.3214 | 10.0 | 100 | 2.2362 | 209.4675 |
73
- | 0.8252 | 15.0 | 150 | 1.8968 | 81.0651 |
74
- | 0.6493 | 20.0 | 200 | 1.8047 | 211.8343 |
75
 
76
 
77
  ### Framework versions
 
23
  metrics:
24
  - name: Wer
25
  type: wer
26
+ value: 67.45562130177515
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on the Nyansapo AI Dataset dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 1.6114
37
+ - Wer: 67.4556
38
 
39
  ## Model description
40
 
 
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 50
65
+ - training_steps: 75
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
70
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
71
+ | 2.2113 | 2.5 | 25 | 2.1600 | 48.5207 |
72
+ | 1.7347 | 5.0 | 50 | 1.7906 | 53.8462 |
73
+ | 1.3358 | 7.5 | 75 | 1.6114 | 67.4556 |
 
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f139aa73b8ea6e701e53920a99651f91374c4129c8efb9755f11928d01aed97f
3
  size 151060136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b09cb128cd56019095d526c1f8e671aa512d99e9d9b3f61cebfca0ca3fd33e3
3
  size 151060136
runs/Mar23_18-30-15_Edwards-MacBook-Pro-2.local/events.out.tfevents.1711233018.Edwards-MacBook-Pro-2.local.80784.5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a12c165059d9a90d685897b2df2111a62e3e599aba12c6f2efee6992d8e6e13c
3
- size 6991
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998bbf65a73aefac50a7627c9d59e9c43ff8a99aaee56d0907912451f01b7382
3
+ size 7339