Hugging Face's logo

Chenchuhui
/
Icelandic-finetuned-no-data-augmentation

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Chenchuhui commited on
Commit
04fd855
•
1 Parent(s): dcbfb5f

End of training

Browse files
Files changed (3) hide show
  1. README.md +60 -3
  2. model.safetensors +1 -1
  3. runs/Dec18_17-04-02_f6af7c3761bc/events.out.tfevents.1702919083.f6af7c3761bc.6609.0 +2 -2
README.md CHANGED
@@ -3,6 +3,8 @@ license: cc-by-4.0
3
  base_model: carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: Icelandic-finetuned-no-data-augmentation
8
  results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
14
  # Icelandic-finetuned-no-data-augmentation
15
 
16
  This model is a fine-tuned version of [carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h](https://huggingface.co/carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h) on the None dataset.
 
 
 
17
 
18
  ## Model description
19
 
@@ -33,11 +38,11 @@ More information needed
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 0.0003
36
- - train_batch_size: 1
37
- - eval_batch_size: 1
38
  - seed: 42
39
  - gradient_accumulation_steps: 2
40
- - total_train_batch_size: 2
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 500
@@ -45,6 +50,58 @@ The following hyperparameters were used during training:
45
 
46
  ### Training results
47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
 
49
 
50
  ### Framework versions
 
3
  base_model: carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - wer
8
  model-index:
9
  - name: Icelandic-finetuned-no-data-augmentation
10
  results: []
 
16
  # Icelandic-finetuned-no-data-augmentation
17
 
18
  This model is a fine-tuned version of [carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h](https://huggingface.co/carlosdanielhernandezmena/wav2vec2-large-xlsr-53-icelandic-ep10-1000h) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.1262
21
+ - Wer: 0.1544
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.0003
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
  - seed: 42
44
  - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 16
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 500
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
55
+ | No log | 0.2 | 10 | 0.2849 | 0.1667 |
56
+ | No log | 0.4 | 20 | 0.3085 | 0.1611 |
57
+ | No log | 0.6 | 30 | 0.3264 | 0.1600 |
58
+ | No log | 0.8 | 40 | 0.3149 | 0.1577 |
59
+ | 0.3456 | 1.0 | 50 | 0.3221 | 0.1588 |
60
+ | 0.3456 | 1.2 | 60 | 0.3183 | 0.1577 |
61
+ | 0.3456 | 1.4 | 70 | 0.3133 | 0.1510 |
62
+ | 0.3456 | 1.6 | 80 | 0.3069 | 0.1521 |
63
+ | 0.3456 | 1.8 | 90 | 0.2970 | 0.1521 |
64
+ | 0.2689 | 2.0 | 100 | 0.2782 | 0.1477 |
65
+ | 0.2689 | 2.2 | 110 | 0.2242 | 0.1488 |
66
+ | 0.2689 | 2.4 | 120 | 0.2257 | 0.1454 |
67
+ | 0.2689 | 2.6 | 130 | 0.2722 | 0.1521 |
68
+ | 0.2689 | 2.8 | 140 | 0.2564 | 0.1488 |
69
+ | 0.2312 | 3.0 | 150 | 0.1811 | 0.1521 |
70
+ | 0.2312 | 3.2 | 160 | 0.1762 | 0.1454 |
71
+ | 0.2312 | 3.4 | 170 | 0.2154 | 0.1421 |
72
+ | 0.2312 | 3.6 | 180 | 0.1873 | 0.1465 |
73
+ | 0.2312 | 3.8 | 190 | 0.2015 | 0.1465 |
74
+ | 0.2153 | 4.0 | 200 | 0.2402 | 0.1499 |
75
+ | 0.2153 | 4.2 | 210 | 0.2366 | 0.1454 |
76
+ | 0.2153 | 4.4 | 220 | 0.1890 | 0.1477 |
77
+ | 0.2153 | 4.6 | 230 | 0.1897 | 0.1499 |
78
+ | 0.2153 | 4.8 | 240 | 0.1777 | 0.1488 |
79
+ | 0.1986 | 5.0 | 250 | 0.1659 | 0.1555 |
80
+ | 0.1986 | 5.2 | 260 | 0.1936 | 0.1588 |
81
+ | 0.1986 | 5.4 | 270 | 0.2044 | 0.1532 |
82
+ | 0.1986 | 5.6 | 280 | 0.1958 | 0.1555 |
83
+ | 0.1986 | 5.8 | 290 | 0.1760 | 0.1521 |
84
+ | 0.1842 | 6.0 | 300 | 0.2056 | 0.1600 |
85
+ | 0.1842 | 6.2 | 310 | 0.1649 | 0.1532 |
86
+ | 0.1842 | 6.4 | 320 | 0.2269 | 0.1532 |
87
+ | 0.1842 | 6.6 | 330 | 0.1572 | 0.1488 |
88
+ | 0.1842 | 6.8 | 340 | 0.1890 | 0.1600 |
89
+ | 0.181 | 7.0 | 350 | 0.1757 | 0.1700 |
90
+ | 0.181 | 7.2 | 360 | 0.2322 | 0.1644 |
91
+ | 0.181 | 7.4 | 370 | 0.2644 | 0.1600 |
92
+ | 0.181 | 7.6 | 380 | 0.2047 | 0.1555 |
93
+ | 0.181 | 7.8 | 390 | 0.2406 | 0.1678 |
94
+ | 0.1751 | 8.0 | 400 | 0.2820 | 0.1678 |
95
+ | 0.1751 | 8.2 | 410 | 0.2965 | 0.1655 |
96
+ | 0.1751 | 8.4 | 420 | 0.2841 | 0.1667 |
97
+ | 0.1751 | 8.6 | 430 | 0.2527 | 0.1734 |
98
+ | 0.1751 | 8.8 | 440 | 0.5464 | 0.1700 |
99
+ | 0.1836 | 9.0 | 450 | 0.2185 | 0.1622 |
100
+ | 0.1836 | 9.2 | 460 | 0.2129 | 0.1857 |
101
+ | 0.1836 | 9.4 | 470 | 0.3367 | 0.1779 |
102
+ | 0.1836 | 9.6 | 480 | 0.1457 | 0.1644 |
103
+ | 0.1836 | 9.8 | 490 | 0.1320 | 0.1667 |
104
+ | 0.2141 | 10.0 | 500 | 0.1262 | 0.1544 |
105
 
106
 
107
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01d165f735037deaf8320aab9765c23d8da5be5b98cab69e29de8046d1e790cf
3
  size 1261967380
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:283e90df1f2b7a39ca4f0a3ebbc5184558f8353a9409e73cb975d65c02d18f61
3
  size 1261967380
runs/Dec18_17-04-02_f6af7c3761bc/events.out.tfevents.1702919083.f6af7c3761bc.6609.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a069cb57802226db21a7cefcc4d75e2f83e814a7bd9cd294316142c1c990218
3
- size 22606
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a3ea842b8dc67593327b86928d7a65792d1569776abe14e41b47d17a9c33e0
3
+ size 23753