Hugging Face's logo

rossevine
/
Model_G_2

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
rossevine commited on
Commit
628c3c6
•
1 Parent(s): 28cc785

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -43
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.9852694387469699
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.0359
36
- - Wer: 0.9853
37
- - Cer: 0.7143
38
 
39
  ## Model description
40
 
@@ -66,45 +66,17 @@ The following hyperparameters were used during training:
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
70
- |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
71
- | 3.8996 | 0.81 | 400 | 0.7268 | 1.0008 | 0.7672 |
72
- | 0.5216 | 1.61 | 800 | 0.2765 | 1.0171 | 0.7602 |
73
- | 0.3112 | 2.42 | 1200 | 0.1712 | 0.9965 | 0.7335 |
74
- | 0.2343 | 3.23 | 1600 | 0.1169 | 0.9984 | 0.7262 |
75
- | 0.1911 | 4.03 | 2000 | 0.0970 | 0.9970 | 0.7447 |
76
- | 0.1625 | 4.84 | 2400 | 0.0834 | 0.9941 | 0.7245 |
77
- | 0.1471 | 5.65 | 2800 | 0.0771 | 0.9936 | 0.7239 |
78
- | 0.1301 | 6.45 | 3200 | 0.0645 | 0.9940 | 0.7330 |
79
- | 0.1241 | 7.26 | 3600 | 0.0621 | 0.9912 | 0.7208 |
80
- | 0.1128 | 8.06 | 4000 | 0.0672 | 0.9892 | 0.7188 |
81
- | 0.1035 | 8.87 | 4400 | 0.0531 | 0.9895 | 0.7332 |
82
- | 0.0993 | 9.68 | 4800 | 0.0541 | 0.9912 | 0.7374 |
83
- | 0.0917 | 10.48 | 5200 | 0.0516 | 0.9883 | 0.7276 |
84
- | 0.0879 | 11.29 | 5600 | 0.0507 | 0.9841 | 0.7246 |
85
- | 0.0836 | 12.1 | 6000 | 0.0490 | 0.9858 | 0.7335 |
86
- | 0.0767 | 12.9 | 6400 | 0.0464 | 0.9844 | 0.7231 |
87
- | 0.0744 | 13.71 | 6800 | 0.0458 | 0.9855 | 0.7170 |
88
- | 0.0695 | 14.52 | 7200 | 0.0506 | 0.9893 | 0.7145 |
89
- | 0.0676 | 15.32 | 7600 | 0.0443 | 0.9892 | 0.7151 |
90
- | 0.0621 | 16.13 | 8000 | 0.0457 | 0.9831 | 0.7188 |
91
- | 0.0593 | 16.94 | 8400 | 0.0437 | 0.9905 | 0.7251 |
92
- | 0.0558 | 17.74 | 8800 | 0.0419 | 0.9881 | 0.7160 |
93
- | 0.0539 | 18.55 | 9200 | 0.0403 | 0.9897 | 0.7128 |
94
- | 0.0509 | 19.35 | 9600 | 0.0435 | 0.9853 | 0.7195 |
95
- | 0.0482 | 20.16 | 10000 | 0.0451 | 0.9863 | 0.7170 |
96
- | 0.0452 | 20.97 | 10400 | 0.0397 | 0.9874 | 0.7128 |
97
- | 0.0438 | 21.77 | 10800 | 0.0378 | 0.9874 | 0.7108 |
98
- | 0.0419 | 22.58 | 11200 | 0.0394 | 0.9881 | 0.7096 |
99
- | 0.0389 | 23.39 | 11600 | 0.0412 | 0.9874 | 0.7105 |
100
- | 0.0377 | 24.19 | 12000 | 0.0388 | 0.9847 | 0.7180 |
101
- | 0.0362 | 25.0 | 12400 | 0.0365 | 0.9848 | 0.7149 |
102
- | 0.0336 | 25.81 | 12800 | 0.0363 | 0.9840 | 0.7144 |
103
- | 0.0315 | 26.61 | 13200 | 0.0366 | 0.9855 | 0.7138 |
104
- | 0.031 | 27.42 | 13600 | 0.0381 | 0.9864 | 0.7171 |
105
- | 0.0303 | 28.23 | 14000 | 0.0363 | 0.9857 | 0.7145 |
106
- | 0.0276 | 29.03 | 14400 | 0.0365 | 0.9854 | 0.7136 |
107
- | 0.0282 | 29.84 | 14800 | 0.0359 | 0.9853 | 0.7143 |
108
 
109
 
110
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.251258623904531
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.3710
36
+ - Wer: 0.2513
37
+ - Cer: 0.0631
38
 
39
  ## Model description
40
 
 
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
70
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
71
+ | 3.7484 | 3.23 | 400 | 0.5706 | 0.5698 | 0.1477 |
72
+ | 0.3419 | 6.45 | 800 | 0.4120 | 0.3758 | 0.0924 |
73
+ | 0.1796 | 9.68 | 1200 | 0.3691 | 0.3295 | 0.0843 |
74
+ | 0.125 | 12.9 | 1600 | 0.3821 | 0.3097 | 0.0782 |
75
+ | 0.0984 | 16.13 | 2000 | 0.4085 | 0.2947 | 0.0742 |
76
+ | 0.0827 | 19.35 | 2400 | 0.3859 | 0.2781 | 0.0711 |
77
+ | 0.0666 | 22.58 | 2800 | 0.3813 | 0.2663 | 0.0684 |
78
+ | 0.0558 | 25.81 | 3200 | 0.3681 | 0.2545 | 0.0644 |
79
+ | 0.0466 | 29.03 | 3600 | 0.3710 | 0.2513 | 0.0631 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
 
81
 
82
  ### Framework versions