Hugging Face's logo

mapau
/
whisper-small-hr

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Croatian
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mapau commited on
Commit
20da83b
•
1 Parent(s): 90fa0cb

End of training

Browse files
Files changed (2) hide show
  1. README.md +12 -11
  2. model.safetensors +1 -1
README.md CHANGED
@@ -24,7 +24,7 @@ model-index:
24
  metrics:
25
  - name: Wer
26
  type: wer
27
- value: 25.56675062972292
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-small](https://huggingface.co/openai/whisper-small) on the parlaSmall_subset dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.5479
38
- - Wer: 25.5668
39
 
40
  ## Model description
41
 
@@ -55,24 +55,25 @@ More information needed
55
 
56
  The following hyperparameters were used during training:
57
  - learning_rate: 1e-05
58
- - train_batch_size: 1
59
  - eval_batch_size: 8
60
  - seed: 42
61
- - gradient_accumulation_steps: 16
62
  - total_train_batch_size: 16
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: linear
65
  - lr_scheduler_warmup_steps: 500
66
- - training_steps: 3000
67
  - mixed_precision_training: Native AMP
68
 
69
  ### Training results
70
 
71
- | Training Loss | Epoch | Step | Validation Loss | Wer |
72
- |:-------------:|:-----:|:----:|:---------------:|:-------:|
73
- | 0.0003 | 32.52 | 1000 | 0.5035 | 26.3224 |
74
- | 0.0001 | 65.04 | 2000 | 0.5380 | 25.8186 |
75
- | 0.0001 | 97.56 | 3000 | 0.5479 | 25.5668 |
 
76
 
77
 
78
  ### Framework versions
 
24
  metrics:
25
  - name: Wer
26
  type: wer
27
+ value: 25.440806045340054
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-small](https://huggingface.co/openai/whisper-small) on the parlaSmall_subset dataset.
36
  It achieves the following results on the evaluation set:
37
+ - Loss: 0.5739
38
+ - Wer: 25.4408
39
 
40
  ## Model description
41
 
 
55
 
56
  The following hyperparameters were used during training:
57
  - learning_rate: 1e-05
58
+ - train_batch_size: 2
59
  - eval_batch_size: 8
60
  - seed: 42
61
+ - gradient_accumulation_steps: 8
62
  - total_train_batch_size: 16
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: linear
65
  - lr_scheduler_warmup_steps: 500
66
+ - training_steps: 4000
67
  - mixed_precision_training: Native AMP
68
 
69
  ### Training results
70
 
71
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
72
+ |:-------------:|:------:|:----:|:---------------:|:-------:|
73
+ | 0.0003 | 32.52 | 1000 | 0.5073 | 25.0630 |
74
+ | 0.0001 | 65.04 | 2000 | 0.5470 | 25.5668 |
75
+ | 0.0001 | 97.56 | 3000 | 0.5668 | 25.0630 |
76
+ | 0.0 | 130.08 | 4000 | 0.5739 | 25.4408 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aca1d7e4c78a89c7bd393a96793059b60b5233e0b9d6ba0bdda86cef635d93fe
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21785a90c2ff94068d372db58168b2776ecf312b8fb8d1912318f300170d3578
3
  size 966995080