Hugging Face's logo

bayartsogt
/
wav2vec2-large-mn-pretrain-42h-100-epochs

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
bayartsogt commited on
Commit
fe708c3
•
1 Parent(s): b57f254

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +88 -0
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice
7
+ model-index:
8
+ - name: wav2vec2-large-mn-pretrain-42h-100-epochs
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # wav2vec2-large-mn-pretrain-42h-100-epochs
16
+
17
+ This model is a fine-tuned version of [bayartsogt/wav2vec2-large-mn-pretrain-42h](https://huggingface.co/bayartsogt/wav2vec2-large-mn-pretrain-42h) on the common_voice dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 6.4172
20
+ - Wer: 1.0
21
+ - Cer: 0.9841
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
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
49
+ - training_steps: 10000
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:---:|:------:|
56
+ | 7.6418 | 1.59 | 400 | 6.4239 | 1.0 | 0.9841 |
57
+ | 5.5936 | 3.19 | 800 | 6.4154 | 1.0 | 0.9841 |
58
+ | 5.5208 | 4.78 | 1200 | 6.5248 | 1.0 | 0.9841 |
59
+ | 5.4869 | 6.37 | 1600 | 6.3805 | 1.0 | 0.9841 |
60
+ | 5.4757 | 7.97 | 2000 | 6.3988 | 1.0 | 0.9841 |
61
+ | 5.4624 | 9.56 | 2400 | 6.4058 | 1.0 | 0.9841 |
62
+ | 5.517 | 11.16 | 2800 | 6.3991 | 1.0 | 0.9841 |
63
+ | 5.4821 | 12.75 | 3200 | 6.4066 | 1.0 | 0.9841 |
64
+ | 5.487 | 14.34 | 3600 | 6.4281 | 1.0 | 0.9841 |
65
+ | 5.4786 | 15.93 | 4000 | 6.4174 | 1.0 | 0.9841 |
66
+ | 5.5017 | 17.53 | 4400 | 6.4338 | 1.0 | 0.9841 |
67
+ | 5.4967 | 19.12 | 4800 | 6.4653 | 1.0 | 0.9841 |
68
+ | 5.4619 | 20.72 | 5200 | 6.4499 | 1.0 | 0.9841 |
69
+ | 5.4883 | 22.31 | 5600 | 6.4345 | 1.0 | 0.9841 |
70
+ | 5.4899 | 23.9 | 6000 | 6.4224 | 1.0 | 0.9841 |
71
+ | 5.493 | 25.5 | 6400 | 6.4374 | 1.0 | 0.9841 |
72
+ | 5.4549 | 27.09 | 6800 | 6.4320 | 1.0 | 0.9841 |
73
+ | 5.4531 | 28.68 | 7200 | 6.4137 | 1.0 | 0.9841 |
74
+ | 5.4738 | 30.28 | 7600 | 6.4155 | 1.0 | 0.9841 |
75
+ | 5.4309 | 31.87 | 8000 | 6.4193 | 1.0 | 0.9841 |
76
+ | 5.4669 | 33.47 | 8400 | 6.4109 | 1.0 | 0.9841 |
77
+ | 5.47 | 35.06 | 8800 | 6.4111 | 1.0 | 0.9841 |
78
+ | 5.4623 | 36.65 | 9200 | 6.4102 | 1.0 | 0.9841 |
79
+ | 5.4583 | 38.25 | 9600 | 6.4150 | 1.0 | 0.9841 |
80
+ | 5.4551 | 39.84 | 10000 | 6.4172 | 1.0 | 0.9841 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.20.1
86
+ - Pytorch 1.11.0
87
+ - Datasets 2.1.0
88
+ - Tokenizers 0.12.1