Hugging Face's logo

KatMarie
/
wav2vec2-large-xls-r-300m-euskera-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
KatMarie commited on
Commit
799d7fa
·
1 Parent(s): ba6a75e

End of training

Browse files
Files changed (2) hide show
  1. README.md +20 -11
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.3909212143398792
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.2684
36
- - Wer: 0.3909
37
 
38
  ## Model description
39
 
@@ -53,25 +53,34 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0003
56
- - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - gradient_accumulation_steps: 2
60
- - total_train_batch_size: 16
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
- - num_epochs: 5
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
- | 4.7119 | 0.85 | 400 | 2.8503 | 1.0 |
71
- | 2.2906 | 1.7 | 800 | 0.6839 | 0.8005 |
72
- | 0.5099 | 2.56 | 1200 | 0.3751 | 0.5345 |
73
- | 0.3403 | 3.41 | 1600 | 0.3170 | 0.4379 |
74
- | 0.2608 | 4.26 | 2000 | 0.2684 | 0.3909 |
 
 
 
 
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.28292759459247446
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 [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.2281
36
+ - Wer: 0.2829
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0003
56
+ - train_batch_size: 4
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - gradient_accumulation_steps: 2
60
+ - total_train_batch_size: 8
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
+ - num_epochs: 6
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 3.6474 | 0.43 | 400 | 0.8974 | 0.9025 |
71
+ | 0.4849 | 0.85 | 800 | 0.4653 | 0.6314 |
72
+ | 0.2924 | 1.28 | 1200 | 0.3726 | 0.5294 |
73
+ | 0.2392 | 1.7 | 1600 | 0.3203 | 0.4461 |
74
+ | 0.1957 | 2.13 | 2000 | 0.2932 | 0.4053 |
75
+ | 0.1592 | 2.56 | 2400 | 0.2767 | 0.3760 |
76
+ | 0.1442 | 2.98 | 2800 | 0.2605 | 0.3635 |
77
+ | 0.1166 | 3.41 | 3200 | 0.2662 | 0.3415 |
78
+ | 0.1064 | 3.84 | 3600 | 0.2576 | 0.3409 |
79
+ | 0.0906 | 4.26 | 4000 | 0.2567 | 0.3234 |
80
+ | 0.0818 | 4.69 | 4400 | 0.2472 | 0.3063 |
81
+ | 0.0701 | 5.11 | 4800 | 0.2440 | 0.2951 |
82
+ | 0.0595 | 5.54 | 5200 | 0.2321 | 0.2810 |
83
+ | 0.0566 | 5.97 | 5600 | 0.2281 | 0.2829 |
84
 
85
 
86
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6b3e1dfd899c5bdc072e4ae643158a61cef85174817f2f9e201290580f24cca
3
  size 1262033069
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f47cf60e66c1b63855d0e7194128d6441a533cd138a7abce5c9ae7e4e96542a
3
  size 1262033069