Hugging Face's logo

ivillar
/
xho_finetune

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ivillar commited on
Commit
4855784
•
1 Parent(s): cb03370

End of training

Browse files
Files changed (2) hide show
  1. README.md +128 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Akashpb13/Swahili_xlsr
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - ml-superb-subset
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: xho_finetune
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: ml-superb-subset
18
+ type: ml-superb-subset
19
+ config: xho
20
+ split: test
21
+ args: xho
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 53.510895883777245
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # xho_finetune
32
+
33
+ This model is a fine-tuned version of [Akashpb13/Swahili_xlsr](https://huggingface.co/Akashpb13/Swahili_xlsr) on the ml-superb-subset dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.5370
36
+ - Wer: 53.5109
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 9.6e-05
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 2
60
+ - total_train_batch_size: 64
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: cosine
63
+ - lr_scheduler_warmup_steps: 25
64
+ - training_steps: 500
65
+ - mixed_precision_training: Native AMP
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
70
+ |:-------------:|:-------:|:----:|:---------------:|:-------:|
71
+ | 25.5184 | 0.7692 | 10 | 24.2275 | 100.0 |
72
+ | 14.5363 | 1.5385 | 20 | 9.8357 | 100.0 |
73
+ | 4.5811 | 2.3077 | 30 | 3.8367 | 100.0 |
74
+ | 3.4822 | 3.0769 | 40 | 3.3922 | 100.0 |
75
+ | 3.2732 | 3.8462 | 50 | 3.2398 | 100.0 |
76
+ | 3.1796 | 4.6154 | 60 | 3.1705 | 100.0 |
77
+ | 3.1504 | 5.3846 | 70 | 3.1419 | 100.0 |
78
+ | 3.1119 | 6.1538 | 80 | 3.1084 | 100.0 |
79
+ | 3.0789 | 6.9231 | 90 | 3.0735 | 100.0 |
80
+ | 3.0619 | 7.6923 | 100 | 3.0590 | 100.0 |
81
+ | 3.0298 | 8.4615 | 110 | 3.0247 | 100.0 |
82
+ | 2.9933 | 9.2308 | 120 | 2.9716 | 100.0 |
83
+ | 2.9079 | 10.0 | 130 | 2.8647 | 100.0 |
84
+ | 2.8414 | 10.7692 | 140 | 2.7931 | 100.0 |
85
+ | 2.6939 | 11.5385 | 150 | 2.5932 | 100.0 |
86
+ | 2.3274 | 12.3077 | 160 | 2.1000 | 99.7579 |
87
+ | 1.7068 | 13.0769 | 170 | 1.4580 | 93.4625 |
88
+ | 1.206 | 13.8462 | 180 | 1.1027 | 83.0508 |
89
+ | 0.9587 | 14.6154 | 190 | 0.9152 | 79.4189 |
90
+ | 0.7806 | 15.3846 | 200 | 0.8122 | 69.7337 |
91
+ | 0.7118 | 16.1538 | 210 | 0.7445 | 69.0073 |
92
+ | 0.6814 | 16.9231 | 220 | 0.6945 | 62.9540 |
93
+ | 0.5709 | 17.6923 | 230 | 0.6787 | 67.5545 |
94
+ | 0.5653 | 18.4615 | 240 | 0.6758 | 62.2276 |
95
+ | 0.5437 | 19.2308 | 250 | 0.6511 | 60.7748 |
96
+ | 0.5092 | 20.0 | 260 | 0.6237 | 62.7119 |
97
+ | 0.4239 | 20.7692 | 270 | 0.6000 | 61.5012 |
98
+ | 0.4355 | 21.5385 | 280 | 0.5899 | 59.8063 |
99
+ | 0.4456 | 22.3077 | 290 | 0.5960 | 59.3220 |
100
+ | 0.3986 | 23.0769 | 300 | 0.5764 | 56.6586 |
101
+ | 0.3856 | 23.8462 | 310 | 0.5801 | 55.9322 |
102
+ | 0.3607 | 24.6154 | 320 | 0.5682 | 57.6271 |
103
+ | 0.358 | 25.3846 | 330 | 0.5675 | 55.9322 |
104
+ | 0.3452 | 26.1538 | 340 | 0.5630 | 57.8692 |
105
+ | 0.3289 | 26.9231 | 350 | 0.5515 | 57.8692 |
106
+ | 0.353 | 27.6923 | 360 | 0.5621 | 57.3850 |
107
+ | 0.2907 | 28.4615 | 370 | 0.5486 | 55.2058 |
108
+ | 0.3237 | 29.2308 | 380 | 0.5445 | 54.4794 |
109
+ | 0.3202 | 30.0 | 390 | 0.5384 | 52.7845 |
110
+ | 0.2918 | 30.7692 | 400 | 0.5370 | 55.6901 |
111
+ | 0.3106 | 31.5385 | 410 | 0.5422 | 53.7530 |
112
+ | 0.3105 | 32.3077 | 420 | 0.5438 | 55.2058 |
113
+ | 0.2835 | 33.0769 | 430 | 0.5437 | 55.9322 |
114
+ | 0.2966 | 33.8462 | 440 | 0.5416 | 54.7215 |
115
+ | 0.2719 | 34.6154 | 450 | 0.5394 | 54.2373 |
116
+ | 0.2859 | 35.3846 | 460 | 0.5384 | 53.7530 |
117
+ | 0.29 | 36.1538 | 470 | 0.5379 | 53.2688 |
118
+ | 0.2879 | 36.9231 | 480 | 0.5372 | 53.5109 |
119
+ | 0.2871 | 37.6923 | 490 | 0.5370 | 53.5109 |
120
+ | 0.3019 | 38.4615 | 500 | 0.5370 | 53.5109 |
121
+
122
+
123
+ ### Framework versions
124
+
125
+ - Transformers 4.41.1
126
+ - Pytorch 2.3.0+cu121
127
+ - Datasets 2.19.1
128
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6160bfb28482cd34a833dadc0b09c8e138d734e74a07ca072616032439c57241
3
  size 1261942780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d2c99e9fc65b1305846507dfcc2f15f3e16049e9d76b7396791140af088ca2d
3
  size 1261942780