Hugging Face's logo

thiagobarbosa
/
whisper-base-google-fleurs-pt-br

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
thiagobarbosa commited on
Commit
cc5552a
·
verified ·
1 Parent(s): 0ac675a

Model save

Browse files
Files changed (2) hide show
  1. README.md +9 -9
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.5030
21
- - Wer: 19.3174
22
 
23
  ## Model description
24
 
@@ -37,25 +37,25 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 5e-05
41
  - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 100
47
- - training_steps: 2000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
54
- | 0.3674 | 0.57 | 400 | 0.4892 | 21.0004 |
55
- | 0.1001 | 1.15 | 800 | 0.5216 | 21.6539 |
56
- | 0.0936 | 1.72 | 1200 | 0.5094 | 20.5303 |
57
- | 0.0347 | 2.3 | 1600 | 0.5013 | 19.2798 |
58
- | 0.0066 | 2.87 | 2000 | 0.5030 | 19.3174 |
59
 
60
 
61
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4732
21
+ - Wer: 18.2079
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 2.5e-05
41
  - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 100
47
+ - training_steps: 4000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
54
+ | 0.382 | 0.57 | 400 | 0.4085 | 18.3348 |
55
+ | 0.1182 | 1.15 | 800 | 0.4220 | 17.7613 |
56
+ | 0.0991 | 1.72 | 1200 | 0.4479 | 19.6230 |
57
+ | 0.0424 | 2.3 | 1600 | 0.4551 | 18.2173 |
58
+ | 0.0458 | 2.87 | 2000 | 0.4732 | 18.2079 |
59
 
60
 
61
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33073d188811651c324e6b7498d4d3aa32ad5deaa9a7ed4a431daedb3cb4c574
3
  size 290459230
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecbe2b889e8805ceaeac4b305e3f6b7f9ae9a0652b9bf9bc3abe289c218dbc15
3
  size 290459230