Hugging Face's logo

tuanio
/
5-epochs5-char-based-freeze_cnn-dropout0.3

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files Community
tuanio commited on
Commit
89a59c8
·
1 Parent(s): 539ce22

End of training

Browse files
Files changed (2) hide show
  1. README.md +138 -0
  2. trainer_state.json +0 -0
README.md ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-xls-r-300m
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: 5-epochs5-char-based-freeze_cnn-dropout0.3
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # 5-epochs5-char-based-freeze_cnn-dropout0.3
17
+
18
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: nan
21
+ - Wer: 1.0
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: 4.000000000000001e-06
41
+ - train_batch_size: 10
42
+ - eval_batch_size: 2
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - total_train_batch_size: 40
47
+ - total_eval_batch_size: 8
48
+ - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 5
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
56
+ |:-------------:|:-----:|:------:|:---------------:|:---:|
57
+ | 10.4529 | 0.07 | 2500 | 21.5863 | 1.0 |
58
+ | 5.5789 | 0.14 | 5000 | 7.7088 | 1.0 |
59
+ | 3.9797 | 0.2 | 7500 | 4.7691 | 1.0 |
60
+ | 3.5344 | 0.27 | 10000 | 3.7288 | 1.0 |
61
+ | 3.5794 | 0.34 | 12500 | 3.8970 | 1.0 |
62
+ | 3.5264 | 0.41 | 15000 | 3.9099 | 1.0 |
63
+ | 3.5346 | 0.47 | 17500 | 3.9135 | 1.0 |
64
+ | 3.6184 | 0.54 | 20000 | 3.9921 | 1.0 |
65
+ | 3.5259 | 0.61 | 22500 | 3.9837 | 1.0 |
66
+ | 3.5744 | 0.68 | 25000 | 3.9882 | 1.0 |
67
+ | 3.5945 | 0.74 | 27500 | 3.7869 | 1.0 |
68
+ | 3.6836 | 0.81 | 30000 | 3.9407 | 1.0 |
69
+ | 3.7874 | 0.88 | 32500 | 3.7358 | 1.0 |
70
+ | 3.7926 | 0.95 | 35000 | 3.7358 | 1.0 |
71
+ | 3.7937 | 1.01 | 37500 | 3.7358 | 1.0 |
72
+ | 3.7933 | 1.08 | 40000 | 3.7358 | 1.0 |
73
+ | 3.7923 | 1.15 | 42500 | 3.7358 | 1.0 |
74
+ | 3.7923 | 1.22 | 45000 | 3.7358 | 1.0 |
75
+ | 3.7965 | 1.28 | 47500 | 3.7358 | 1.0 |
76
+ | 3.7942 | 1.35 | 50000 | 3.7358 | 1.0 |
77
+ | 3.7934 | 1.42 | 52500 | 3.7358 | 1.0 |
78
+ | 3.7851 | 1.49 | 55000 | 3.7358 | 1.0 |
79
+ | 3.7826 | 1.55 | 57500 | 3.7358 | 1.0 |
80
+ | 3.7891 | 1.62 | 60000 | 3.7358 | 1.0 |
81
+ | 3.7992 | 1.69 | 62500 | 3.7358 | 1.0 |
82
+ | 3.8099 | 1.76 | 65000 | 3.7358 | 1.0 |
83
+ | 3.7788 | 1.82 | 67500 | 3.7358 | 1.0 |
84
+ | 3.7816 | 1.89 | 70000 | 3.7358 | 1.0 |
85
+ | 3.7846 | 1.96 | 72500 | 3.7358 | 1.0 |
86
+ | 3.783 | 2.03 | 75000 | 3.7358 | 1.0 |
87
+ | 3.8451 | 2.09 | 77500 | 3.7358 | 1.0 |
88
+ | 3.7883 | 2.16 | 80000 | 3.7358 | 1.0 |
89
+ | 3.7915 | 2.23 | 82500 | 3.7358 | 1.0 |
90
+ | 3.7688 | 2.3 | 85000 | 3.7358 | 1.0 |
91
+ | 3.7959 | 2.36 | 87500 | 3.7358 | 1.0 |
92
+ | 3.7794 | 2.43 | 90000 | 3.7358 | 1.0 |
93
+ | 3.7862 | 2.5 | 92500 | 3.7358 | 1.0 |
94
+ | 3.8008 | 2.57 | 95000 | 3.7358 | 1.0 |
95
+ | 3.793 | 2.63 | 97500 | 3.7358 | 1.0 |
96
+ | 3.7781 | 2.7 | 100000 | 3.7358 | 1.0 |
97
+ | 3.7878 | 2.77 | 102500 | 3.7358 | 1.0 |
98
+ | 3.836 | 2.84 | 105000 | 3.7358 | 1.0 |
99
+ | 3.7914 | 2.9 | 107500 | 3.7358 | 1.0 |
100
+ | 3.7886 | 2.97 | 110000 | 3.7358 | 1.0 |
101
+ | 3.7924 | 3.04 | 112500 | 3.7358 | 1.0 |
102
+ | 3.7866 | 3.11 | 115000 | 3.7358 | 1.0 |
103
+ | 3.8027 | 3.17 | 117500 | 3.7358 | 1.0 |
104
+ | 0.0 | 3.24 | 120000 | nan | 1.0 |
105
+ | 0.0 | 3.31 | 122500 | nan | 1.0 |
106
+ | 0.0 | 3.38 | 125000 | nan | 1.0 |
107
+ | 0.0 | 3.44 | 127500 | nan | 1.0 |
108
+ | 0.0 | 3.51 | 130000 | nan | 1.0 |
109
+ | 0.0 | 3.58 | 132500 | nan | 1.0 |
110
+ | 0.0 | 3.65 | 135000 | nan | 1.0 |
111
+ | 0.0 | 3.71 | 137500 | nan | 1.0 |
112
+ | 0.0 | 3.78 | 140000 | nan | 1.0 |
113
+ | 0.0 | 3.85 | 142500 | nan | 1.0 |
114
+ | 0.0 | 3.92 | 145000 | nan | 1.0 |
115
+ | 0.0 | 3.98 | 147500 | nan | 1.0 |
116
+ | 0.0 | 4.05 | 150000 | nan | 1.0 |
117
+ | 0.0 | 4.12 | 152500 | nan | 1.0 |
118
+ | 0.0 | 4.19 | 155000 | nan | 1.0 |
119
+ | 0.0 | 4.26 | 157500 | nan | 1.0 |
120
+ | 0.0 | 4.32 | 160000 | nan | 1.0 |
121
+ | 0.0 | 4.39 | 162500 | nan | 1.0 |
122
+ | 0.0 | 4.46 | 165000 | nan | 1.0 |
123
+ | 0.0 | 4.53 | 167500 | nan | 1.0 |
124
+ | 0.0 | 4.59 | 170000 | nan | 1.0 |
125
+ | 0.0 | 4.66 | 172500 | nan | 1.0 |
126
+ | 0.0 | 4.73 | 175000 | nan | 1.0 |
127
+ | 0.0 | 4.8 | 177500 | nan | 1.0 |
128
+ | 0.0 | 4.86 | 180000 | nan | 1.0 |
129
+ | 0.0 | 4.93 | 182500 | nan | 1.0 |
130
+ | 0.0 | 5.0 | 185000 | nan | 1.0 |
131
+
132
+
133
+ ### Framework versions
134
+
135
+ - Transformers 4.34.0
136
+ - Pytorch 2.0.1
137
+ - Datasets 2.14.5
138
+ - Tokenizers 0.14.1
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff