Hugging Face's logo

Kabul7785
/
xls-r-uzbek-cv8

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Uzbek
wav2vec2
mozilla-foundation/common_voice_8_0
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Kabul7785 commited on
Commit
5233aec
•
1 Parent(s): 6cce3d7

Model save

Browse files
Files changed (3) hide show
  1. README.md +103 -0
  2. model.safetensors +1 -1
  3. runs/May10_16-01-02_mypc/events.out.tfevents.1715339004.mypc.12097.0 +2 -2
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_8_0
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: xls-r-uzbek-cv8
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: common_voice_8_0
18
+ type: common_voice_8_0
19
+ config: uz
20
+ split: validation[50%:]
21
+ args: uz
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.3785223774567843
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-uzbek-cv8
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_8_0 dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.2927
36
+ - Wer: 0.3785
37
+ - Cer: 0.0760
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 3e-05
57
+ - train_batch_size: 4
58
+ - eval_batch_size: 4
59
+ - seed: 42
60
+ - gradient_accumulation_steps: 4
61
+ - total_train_batch_size: 16
62
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
+ - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_steps: 500
65
+ - num_epochs: 10.0
66
+ - mixed_precision_training: Native AMP
67
+
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
71
+ |:-------------:|:------:|:-----:|:---------------:|:------:|:------:|
72
+ | 3.1444 | 0.4055 | 500 | 3.1200 | 1.0 | 1.0 |
73
+ | 2.9488 | 0.8110 | 1000 | 2.9562 | 1.0 | 0.9807 |
74
+ | 1.4553 | 1.2165 | 1500 | 0.7868 | 0.7034 | 0.1644 |
75
+ | 1.1495 | 1.6221 | 2000 | 0.5598 | 0.6076 | 0.1337 |
76
+ | 1.041 | 2.0276 | 2500 | 0.4650 | 0.5537 | 0.1174 |
77
+ | 0.9524 | 2.4331 | 3000 | 0.4204 | 0.5098 | 0.1061 |
78
+ | 0.902 | 2.8386 | 3500 | 0.3919 | 0.4984 | 0.1026 |
79
+ | 0.8505 | 3.2441 | 4000 | 0.3688 | 0.4678 | 0.0965 |
80
+ | 0.8353 | 3.6496 | 4500 | 0.3491 | 0.4488 | 0.0915 |
81
+ | 0.8015 | 4.0552 | 5000 | 0.3410 | 0.4356 | 0.0896 |
82
+ | 0.7771 | 4.4607 | 5500 | 0.3367 | 0.4330 | 0.0883 |
83
+ | 0.7894 | 4.8662 | 6000 | 0.3274 | 0.4201 | 0.0858 |
84
+ | 0.7624 | 5.2717 | 6500 | 0.3266 | 0.4115 | 0.0835 |
85
+ | 0.7522 | 5.6772 | 7000 | 0.3172 | 0.4072 | 0.0825 |
86
+ | 0.7545 | 6.0827 | 7500 | 0.3096 | 0.4034 | 0.0817 |
87
+ | 0.7412 | 6.4882 | 8000 | 0.3062 | 0.4014 | 0.0810 |
88
+ | 0.7405 | 6.8938 | 8500 | 0.3057 | 0.3933 | 0.0796 |
89
+ | 0.703 | 7.2993 | 9000 | 0.2966 | 0.3894 | 0.0784 |
90
+ | 0.7091 | 7.7048 | 9500 | 0.3000 | 0.3895 | 0.0784 |
91
+ | 0.7117 | 8.1103 | 10000 | 0.2988 | 0.3881 | 0.0781 |
92
+ | 0.6871 | 8.5158 | 10500 | 0.2939 | 0.3832 | 0.0771 |
93
+ | 0.6942 | 8.9213 | 11000 | 0.2950 | 0.3816 | 0.0766 |
94
+ | 0.6919 | 9.3268 | 11500 | 0.2910 | 0.3781 | 0.0760 |
95
+ | 0.6756 | 9.7324 | 12000 | 0.2927 | 0.3785 | 0.0760 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.40.2
101
+ - Pytorch 2.3.0+cu118
102
+ - Datasets 2.19.1
103
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b196ae66ed6140972171e52083cce926858c1b388cf45b7b827dd662c3a44ba6
3
  size 1261942780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d03908038cf98752bde44d41d8a03e2c2cf075502a7dc238c3c72f9f7475fb3
3
  size 1261942780
runs/May10_16-01-02_mypc/events.out.tfevents.1715339004.mypc.12097.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b82b7b17ba98e30659cb5bef09663894387c8df2e2b9988c1e4c0ce4d0e8de3e
3
- size 40155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36f6020a68f5bf6c357a667ea5bf83b7895a7845901b9c55430628e1bf19fe55
3
+ size 41142