Yasinjan99 commited on
Commit
8f60edc
1 Parent(s): 63f9024

Model save

Browse files
Files changed (2) hide show
  1. README.md +100 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-xls-r-300m
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - common_voice_11_0
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: xls-r-uyghur-cv11
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: common_voice_11_0
18
+ type: common_voice_11_0
19
+ config: ug
20
+ split: test
21
+ args: ug
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.32705699280295664
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
+ # xls-r-uyghur-cv11
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_11_0 dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.2203
36
+ - Wer: 0.3271
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: 0.0001
56
+ - train_batch_size: 16
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 64
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_steps: 2000
64
+ - num_epochs: 100.0
65
+ - mixed_precision_training: Native AMP
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
70
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
71
+ | 3.3958 | 4.36 | 500 | 3.3137 | 1.0 |
72
+ | 3.032 | 8.71 | 1000 | 2.8586 | 0.9993 |
73
+ | 1.3977 | 13.07 | 1500 | 0.4786 | 0.6375 |
74
+ | 1.2751 | 17.43 | 2000 | 0.3816 | 0.5393 |
75
+ | 1.2113 | 21.79 | 2500 | 0.3451 | 0.5099 |
76
+ | 1.156 | 26.14 | 3000 | 0.3245 | 0.4919 |
77
+ | 1.1226 | 30.5 | 3500 | 0.2992 | 0.4441 |
78
+ | 1.0913 | 34.86 | 4000 | 0.2831 | 0.4315 |
79
+ | 1.0615 | 39.22 | 4500 | 0.2808 | 0.4340 |
80
+ | 1.0455 | 43.57 | 5000 | 0.2713 | 0.4088 |
81
+ | 1.0228 | 47.93 | 5500 | 0.2622 | 0.3960 |
82
+ | 0.9936 | 52.29 | 6000 | 0.2525 | 0.3796 |
83
+ | 0.968 | 56.64 | 6500 | 0.2506 | 0.3798 |
84
+ | 0.9704 | 61.0 | 7000 | 0.2481 | 0.3735 |
85
+ | 0.9552 | 65.36 | 7500 | 0.2394 | 0.3643 |
86
+ | 0.9417 | 69.72 | 8000 | 0.2350 | 0.3537 |
87
+ | 0.9215 | 74.07 | 8500 | 0.2326 | 0.3507 |
88
+ | 0.9097 | 78.43 | 9000 | 0.2277 | 0.3487 |
89
+ | 0.9003 | 82.79 | 9500 | 0.2230 | 0.3362 |
90
+ | 0.8857 | 87.15 | 10000 | 0.2246 | 0.3362 |
91
+ | 0.882 | 91.5 | 10500 | 0.2236 | 0.3315 |
92
+ | 0.8719 | 95.86 | 11000 | 0.2203 | 0.3271 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.35.2
98
+ - Pytorch 2.1.1+cu121
99
+ - Datasets 2.15.0
100
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:440d0a7c916483b31770c738e08756b98d3a642d8c9d2b4cd697fb1e67d0d763
3
  size 1261975580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92c6f002f3a183c616cc622bfbef0d12a8dac0fcaf2b67749985274510457248
3
  size 1261975580