Hugging Face's logo

S-Sethisak
/
xlsr

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
S-Sethisak commited on
Commit
0355575
·
verified ·
1 Parent(s): e96e112

End of training

Browse files
Files changed (2) hide show
  1. README.md +96 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: S-Sethisak/xlsr-khmer-fleur-ex02
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - fleurs
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: xlsr
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: fleurs
18
+ type: fleurs
19
+ config: km_kh
20
+ split: None
21
+ args: km_kh
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.6776300222422034
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
+ # xlsr
32
+
33
+ This model is a fine-tuned version of [S-Sethisak/xlsr-khmer-fleur-ex02](https://huggingface.co/S-Sethisak/xlsr-khmer-fleur-ex02) on the fleurs dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.8011
36
+ - Wer: 0.6776
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: 6.25e-06
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_steps: 800
62
+ - training_steps: 8000
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:------:|:----:|:---------------:|:------:|
69
+ | 2.1893 | 0.1434 | 400 | 1.3998 | 1.0 |
70
+ | 1.7694 | 0.2867 | 800 | 0.9742 | 0.9704 |
71
+ | 1.7196 | 0.4301 | 1200 | 0.8980 | 0.7788 |
72
+ | 1.8691 | 0.5735 | 1600 | 0.8685 | 0.7422 |
73
+ | 1.8432 | 0.7168 | 2000 | 0.8528 | 0.7295 |
74
+ | 1.8607 | 0.8602 | 2400 | 0.8395 | 0.7231 |
75
+ | 1.7744 | 1.0036 | 2800 | 0.8338 | 0.7122 |
76
+ | 1.6846 | 1.1470 | 3200 | 0.8259 | 0.7024 |
77
+ | 1.7989 | 1.2903 | 3600 | 0.8297 | 0.6974 |
78
+ | 1.5462 | 1.4337 | 4000 | 0.8212 | 0.6938 |
79
+ | 1.6145 | 1.5771 | 4400 | 0.8214 | 0.6908 |
80
+ | 1.4987 | 1.7204 | 4800 | 0.8172 | 0.6854 |
81
+ | 1.5861 | 1.8638 | 5200 | 0.8185 | 0.6835 |
82
+ | 1.6129 | 2.0072 | 5600 | 0.8144 | 0.6810 |
83
+ | 1.6523 | 2.1505 | 6000 | 0.8170 | 0.6788 |
84
+ | 1.5069 | 2.2939 | 6400 | 0.8116 | 0.6793 |
85
+ | 1.5815 | 2.4373 | 6800 | 0.8113 | 0.6780 |
86
+ | 1.4807 | 2.5806 | 7200 | 0.8069 | 0.6768 |
87
+ | 1.6869 | 2.7240 | 7600 | 0.8024 | 0.6777 |
88
+ | 1.712 | 2.8674 | 8000 | 0.8011 | 0.6776 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.52.4
94
+ - Pytorch 2.6.0+cu124
95
+ - Datasets 3.6.0
96
+ - Tokenizers 0.21.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f11ce6e3f843514a650e05d66f6f1843ef62ffb772ab02145dd76c94221f299
3
  size 1262106780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640c81c7b8aa7d3055ab0eca06b3ce5e7b39c014743eb204dcbc44e048b26eac
3
  size 1262106780