Hugging Face's logo

DRAGOO
/
assis

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
3
DRAGOO commited on
Commit
7fc6066
•
1 Parent(s): ccb23f4

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +51 -51
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.3836
20
  - Wer: 1
21
 
22
  ## Model description
@@ -52,56 +52,56 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:---:|
55
- | 23.2159 | 0.6 | 100 | 22.1148 | 1 |
56
- | 18.1848 | 1.2 | 200 | 16.7223 | 1 |
57
- | 9.7817 | 1.8 | 300 | 7.9404 | 1 |
58
- | 4.5091 | 2.4 | 400 | 3.7900 | 1 |
59
- | 3.4946 | 2.99 | 500 | 3.2953 | 1 |
60
- | 3.3286 | 3.59 | 600 | 3.1827 | 1 |
61
- | 3.2078 | 4.19 | 700 | 3.1068 | 1 |
62
- | 3.1528 | 4.79 | 800 | 3.0573 | 1 |
63
- | 3.0709 | 5.39 | 900 | 3.0196 | 1 |
64
- | 3.0163 | 5.99 | 1000 | 2.9919 | 1 |
65
- | 2.9789 | 6.59 | 1100 | 2.9504 | 1 |
66
- | 2.9468 | 7.19 | 1200 | 2.9272 | 1 |
67
- | 2.9389 | 7.78 | 1300 | 2.9129 | 1 |
68
- | 2.9192 | 8.38 | 1400 | 2.9005 | 1 |
69
- | 2.9069 | 8.98 | 1500 | 2.8861 | 1 |
70
- | 2.9074 | 9.58 | 1600 | 2.8816 | 1 |
71
- | 2.883 | 10.18 | 1700 | 2.8746 | 1 |
72
- | 2.8746 | 10.78 | 1800 | 2.8718 | 1 |
73
- | 2.8637 | 11.38 | 1900 | 2.8567 | 1 |
74
- | 2.8613 | 11.98 | 2000 | 2.8570 | 1 |
75
- | 2.8598 | 12.57 | 2100 | 2.8449 | 1 |
76
- | 2.8357 | 13.17 | 2200 | 2.8393 | 1 |
77
- | 2.8352 | 13.77 | 2300 | 2.8350 | 1 |
78
- | 2.8178 | 14.37 | 2400 | 2.7879 | 1 |
79
- | 2.5089 | 14.97 | 2500 | 2.3686 | 1 |
80
- | 2.0826 | 15.57 | 2600 | 1.8915 | 1 |
81
- | 1.6003 | 16.17 | 2700 | 1.3513 | 1 |
82
- | 1.2925 | 16.77 | 2800 | 1.0568 | 1 |
83
- | 1.0837 | 17.37 | 2900 | 0.8760 | 1 |
84
- | 0.9333 | 17.96 | 3000 | 0.7588 | 1 |
85
- | 0.8214 | 18.56 | 3100 | 0.6841 | 1 |
86
- | 0.7302 | 19.16 | 3200 | 0.6099 | 1 |
87
- | 0.6815 | 19.76 | 3300 | 0.5459 | 1 |
88
- | 0.6548 | 20.36 | 3400 | 0.5087 | 1 |
89
- | 0.569 | 20.96 | 3500 | 0.4853 | 1 |
90
- | 0.5919 | 21.56 | 3600 | 0.4666 | 1 |
91
- | 0.5306 | 22.16 | 3700 | 0.4508 | 1 |
92
- | 0.5228 | 22.75 | 3800 | 0.4389 | 1 |
93
- | 0.5263 | 23.35 | 3900 | 0.4287 | 1 |
94
- | 0.4945 | 23.95 | 4000 | 0.4182 | 1 |
95
- | 0.4809 | 24.55 | 4100 | 0.4122 | 1 |
96
- | 0.4813 | 25.15 | 4200 | 0.4112 | 1 |
97
- | 0.4664 | 25.75 | 4300 | 0.3972 | 1 |
98
- | 0.455 | 26.35 | 4400 | 0.3950 | 1 |
99
- | 0.4415 | 26.95 | 4500 | 0.3962 | 1 |
100
- | 0.4399 | 27.54 | 4600 | 0.3930 | 1 |
101
- | 0.4451 | 28.14 | 4700 | 0.3864 | 1 |
102
- | 0.4343 | 28.74 | 4800 | 0.3867 | 1 |
103
- | 0.4418 | 29.34 | 4900 | 0.3865 | 1 |
104
- | 0.4223 | 29.94 | 5000 | 0.3836 | 1 |
105
 
106
 
107
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.8484
20
  - Wer: 1
21
 
22
  ## Model description
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:---:|
55
+ | 22.3611 | 0.45 | 100 | 25.5854 | 1 |
56
+ | 20.8274 | 0.9 | 200 | 20.4977 | 1 |
57
+ | 12.1089 | 1.35 | 300 | 11.0220 | 1 |
58
+ | 5.043 | 1.81 | 400 | 4.3838 | 1 |
59
+ | 3.788 | 2.26 | 500 | 3.5831 | 1 |
60
+ | 3.445 | 2.71 | 600 | 3.4112 | 1 |
61
+ | 3.3042 | 3.16 | 700 | 3.3104 | 1 |
62
+ | 3.221 | 3.61 | 800 | 3.2255 | 1 |
63
+ | 3.1628 | 4.06 | 900 | 3.1618 | 1 |
64
+ | 3.0645 | 4.51 | 1000 | 3.1010 | 1 |
65
+ | 3.0913 | 4.97 | 1100 | 3.0624 | 1 |
66
+ | 3.0819 | 5.42 | 1200 | 3.0136 | 1 |
67
+ | 2.9502 | 5.87 | 1300 | 2.9883 | 1 |
68
+ | 2.9611 | 6.32 | 1400 | 2.9651 | 1 |
69
+ | 2.9287 | 6.77 | 1500 | 2.9474 | 1 |
70
+ | 2.9461 | 7.22 | 1600 | 2.9280 | 1 |
71
+ | 2.9176 | 7.67 | 1700 | 2.9148 | 1 |
72
+ | 2.8986 | 8.13 | 1800 | 2.9138 | 1 |
73
+ | 2.8896 | 8.58 | 1900 | 2.9050 | 1 |
74
+ | 2.8879 | 9.03 | 2000 | 2.9093 | 1 |
75
+ | 2.9085 | 9.48 | 2100 | 2.8998 | 1 |
76
+ | 2.876 | 9.93 | 2200 | 2.8807 | 1 |
77
+ | 2.8649 | 10.38 | 2300 | 2.8734 | 1 |
78
+ | 2.8653 | 10.84 | 2400 | 2.8681 | 1 |
79
+ | 2.8683 | 11.29 | 2500 | 2.8596 | 1 |
80
+ | 2.8452 | 11.74 | 2600 | 2.8667 | 1 |
81
+ | 2.8468 | 12.19 | 2700 | 2.8514 | 1 |
82
+ | 2.846 | 12.64 | 2800 | 2.8541 | 1 |
83
+ | 2.8415 | 13.09 | 2900 | 2.8493 | 1 |
84
+ | 2.8195 | 13.54 | 3000 | 2.8472 | 1 |
85
+ | 2.8103 | 14.0 | 3100 | 2.8244 | 1 |
86
+ | 2.6495 | 14.45 | 3200 | 2.5809 | 1 |
87
+ | 2.3126 | 14.9 | 3300 | 2.1612 | 1 |
88
+ | 1.92 | 15.35 | 3400 | 1.7312 | 1 |
89
+ | 1.5734 | 15.8 | 3500 | 1.4245 | 1 |
90
+ | 1.4081 | 16.25 | 3600 | 1.2659 | 1 |
91
+ | 1.2573 | 16.7 | 3700 | 1.1694 | 1 |
92
+ | 1.194 | 17.16 | 3800 | 1.0930 | 1 |
93
+ | 1.1053 | 17.61 | 3900 | 1.0393 | 1 |
94
+ | 1.072 | 18.06 | 4000 | 0.9792 | 1 |
95
+ | 1.0148 | 18.51 | 4100 | 0.9468 | 1 |
96
+ | 0.9995 | 18.96 | 4200 | 0.9228 | 1 |
97
+ | 0.9688 | 19.41 | 4300 | 0.9071 | 1 |
98
+ | 0.956 | 19.86 | 4400 | 0.8950 | 1 |
99
+ | 0.9565 | 20.32 | 4500 | 0.8632 | 1 |
100
+ | 0.9215 | 20.77 | 4600 | 0.8673 | 1 |
101
+ | 0.9006 | 21.22 | 4700 | 0.8647 | 1 |
102
+ | 0.8645 | 21.67 | 4800 | 0.8566 | 1 |
103
+ | 0.8768 | 22.12 | 4900 | 0.8527 | 1 |
104
+ | 0.8809 | 22.57 | 5000 | 0.8484 | 1 |
105
 
106
 
107
  ### Framework versions