Hugging Face's logo

rambaldi47
/
whisper-tiny

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
rambaldi47 commited on
Commit
04cffc7
•
1 Parent(s): 6d8acdc

End of training

Browse files
Files changed (3) hide show
  1. README.md +11 -10
  2. model.safetensors +1 -1
  3. runs/Feb04_23-19-04_MSI/events.out.tfevents.1707088746.MSI +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.4244391971664699
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.6467
36
- - Wer Ortho: 0.4534
37
- - Wer: 0.4244
38
 
39
  ## Model description
40
 
@@ -53,24 +53,25 @@ More information needed
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
- - learning_rate: 4e-06
57
  - train_batch_size: 16
58
  - eval_batch_size: 16
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: constant_with_warmup
62
  - lr_scheduler_warmup_steps: 50
63
- - training_steps: 200
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
70
- | 0.1212 | 1.79 | 50 | 0.5863 | 0.4584 | 0.4085 |
71
- | 0.0775 | 3.57 | 100 | 0.5957 | 0.4442 | 0.3991 |
72
- | 0.0415 | 5.36 | 150 | 0.6280 | 0.4399 | 0.4091 |
73
- | 0.0208 | 7.14 | 200 | 0.6467 | 0.4534 | 0.4244 |
 
74
 
75
 
76
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.4167650531286895
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.6416
36
+ - Wer Ortho: 0.4448
37
+ - Wer: 0.4168
38
 
39
  ## Model description
40
 
 
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
+ - learning_rate: 3e-06
57
  - train_batch_size: 16
58
  - eval_batch_size: 16
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: constant_with_warmup
62
  - lr_scheduler_warmup_steps: 50
63
+ - training_steps: 125
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
70
+ | 0.0592 | 0.89 | 25 | 0.6009 | 0.4226 | 0.3808 |
71
+ | 0.0508 | 1.79 | 50 | 0.6093 | 0.4485 | 0.4103 |
72
+ | 0.0483 | 2.68 | 75 | 0.6205 | 0.4442 | 0.4126 |
73
+ | 0.0315 | 3.57 | 100 | 0.6268 | 0.4392 | 0.4120 |
74
+ | 0.0304 | 4.46 | 125 | 0.6416 | 0.4448 | 0.4168 |
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ba16402eee903e545e926cfdd6a9a326f94261ec73bd52ddb8abc3735833c17
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b279f6c297271b2925b1ee0d429e25de539e0e15e46a18c63a52cfe307dbb385
3
  size 151061672
runs/Feb04_23-19-04_MSI/events.out.tfevents.1707088746.MSI CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ede7a8ffa2b1c1c48e8f08f69020852961c19bdcceddd678957bf5c8ae1b6aea
3
- size 7835
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:143b6d32c1dd21695ed6ace6392ec7cc59c052d7fad512f9693fdd8543816ca9
3
+ size 9065