Hugging Face's logo

Rolv-Arild
/
xls-r-300m-npsc-seq2seq

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
speech-encoder-decoder
Generated from Trainer
Model card Files Metrics Community
1
Rolv-Arild commited on
Commit
d5033e4
·
1 Parent(s): f85d480

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +43 -43
README.md CHANGED
@@ -13,8 +13,8 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model was trained from scratch on the None dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 0.3350
17
- - Wer: 0.3441
18
 
19
  ## Model description
20
 
@@ -33,7 +33,7 @@ More information needed
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
- - learning_rate: 0.0003
37
  - train_batch_size: 8
38
  - eval_batch_size: 8
39
  - seed: 42
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
41
  - total_train_batch_size: 64
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
- - lr_scheduler_warmup_steps: 400
45
  - num_epochs: 20.0
46
  - mixed_precision_training: Native AMP
47
 
@@ -49,45 +49,45 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Wer |
51
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
52
- | 2.2943 | 0.51 | 400 | 4.4367 | 0.9745 |
53
- | 2.8816 | 1.02 | 800 | 2.8103 | 1.2576 |
54
- | 2.7842 | 1.53 | 1200 | 2.6832 | 1.1330 |
55
- | 2.313 | 2.04 | 1600 | 2.6678 | 1.1348 |
56
- | 2.2897 | 2.55 | 2000 | 2.5744 | 1.2102 |
57
- | 1.3821 | 3.06 | 2400 | 2.9908 | 0.9377 |
58
- | 1.074 | 3.57 | 2800 | 2.6649 | 0.8966 |
59
- | 1.3643 | 4.08 | 3200 | 1.0064 | 0.7236 |
60
- | 0.8286 | 4.59 | 3600 | 0.6339 | 0.5454 |
61
- | 0.3872 | 5.1 | 4000 | 0.5170 | 0.4718 |
62
- | 0.3654 | 5.61 | 4400 | 0.4386 | 0.4420 |
63
- | 0.2672 | 6.12 | 4800 | 0.5186 | 0.4679 |
64
- | 0.2519 | 6.63 | 5200 | 0.4238 | 0.4177 |
65
- | 0.3293 | 7.14 | 5600 | 0.3584 | 0.3970 |
66
- | 0.314 | 7.65 | 6000 | 0.3325 | 0.3911 |
67
- | 0.1698 | 8.16 | 6400 | 0.3411 | 0.3855 |
68
- | 0.1682 | 8.67 | 6800 | 0.3239 | 0.3801 |
69
- | 0.1325 | 9.18 | 7200 | 0.3474 | 0.3832 |
70
- | 0.1577 | 9.69 | 7600 | 0.3289 | 0.3839 |
71
- | 0.2259 | 10.2 | 8000 | 0.3183 | 0.3756 |
72
- | 0.2473 | 10.71 | 8400 | 0.3132 | 0.3654 |
73
- | 0.1136 | 11.22 | 8800 | 0.3242 | 0.3670 |
74
- | 0.108 | 11.73 | 9200 | 0.3201 | 0.3601 |
75
- | 0.0806 | 12.24 | 9600 | 0.3223 | 0.3609 |
76
- | 0.0896 | 12.75 | 10000 | 0.3228 | 0.3584 |
77
- | 0.1642 | 13.27 | 10400 | 0.3140 | 0.3547 |
78
- | 0.1442 | 13.77 | 10800 | 0.3235 | 0.3539 |
79
- | 0.0802 | 14.29 | 11200 | 0.3175 | 0.3553 |
80
- | 0.0747 | 14.8 | 11600 | 0.3126 | 0.3512 |
81
- | 0.0488 | 15.31 | 12000 | 0.3292 | 0.3525 |
82
- | 0.0469 | 15.82 | 12400 | 0.3231 | 0.3504 |
83
- | 0.1021 | 16.33 | 12800 | 0.3230 | 0.3502 |
84
- | 0.0841 | 16.84 | 13200 | 0.3348 | 0.3513 |
85
- | 0.0502 | 17.35 | 13600 | 0.3318 | 0.3486 |
86
- | 0.059 | 17.86 | 14000 | 0.3359 | 0.3462 |
87
- | 0.0417 | 18.37 | 14400 | 0.3310 | 0.3467 |
88
- | 0.0322 | 18.88 | 14800 | 0.3325 | 0.3467 |
89
- | 0.0531 | 19.39 | 15200 | 0.3357 | 0.3449 |
90
- | 0.0623 | 19.9 | 15600 | 0.3350 | 0.3441 |
91
 
92
 
93
  ### Framework versions
 
13
 
14
  This model was trained from scratch on the None dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 0.2965
17
+ - Wer: 0.3144
18
 
19
  ## Model description
20
 
 
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
+ - learning_rate: 0.0001
37
  - train_batch_size: 8
38
  - eval_batch_size: 8
39
  - seed: 42
 
41
  - total_train_batch_size: 64
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 1000
45
  - num_epochs: 20.0
46
  - mixed_precision_training: Native AMP
47
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Wer |
51
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
52
+ | 2.888 | 0.51 | 400 | 3.7320 | 0.9440 |
53
+ | 3.1636 | 1.02 | 800 | 2.9188 | 1.1916 |
54
+ | 2.773 | 1.53 | 1200 | 2.3347 | 1.0134 |
55
+ | 0.7198 | 2.04 | 1600 | 0.6678 | 0.4826 |
56
+ | 0.5255 | 2.55 | 2000 | 0.4605 | 0.4135 |
57
+ | 0.3961 | 3.06 | 2400 | 0.4266 | 0.3955 |
58
+ | 0.3424 | 3.57 | 2800 | 0.3786 | 0.3741 |
59
+ | 0.3858 | 4.08 | 3200 | 0.3161 | 0.3552 |
60
+ | 0.3218 | 4.59 | 3600 | 0.3029 | 0.3510 |
61
+ | 0.199 | 5.1 | 4000 | 0.2988 | 0.3418 |
62
+ | 0.2054 | 5.61 | 4400 | 0.2873 | 0.3434 |
63
+ | 0.1704 | 6.12 | 4800 | 0.3129 | 0.3432 |
64
+ | 0.1805 | 6.63 | 5200 | 0.2963 | 0.3413 |
65
+ | 0.2091 | 7.14 | 5600 | 0.2755 | 0.3329 |
66
+ | 0.1971 | 7.65 | 6000 | 0.2706 | 0.3309 |
67
+ | 0.1237 | 8.16 | 6400 | 0.2823 | 0.3270 |
68
+ | 0.123 | 8.67 | 6800 | 0.2754 | 0.3246 |
69
+ | 0.103 | 9.18 | 7200 | 0.2917 | 0.3272 |
70
+ | 0.1143 | 9.69 | 7600 | 0.2885 | 0.3305 |
71
+ | 0.156 | 10.2 | 8000 | 0.2810 | 0.3288 |
72
+ | 0.167 | 10.71 | 8400 | 0.2689 | 0.3232 |
73
+ | 0.0815 | 11.22 | 8800 | 0.2899 | 0.3236 |
74
+ | 0.0844 | 11.73 | 9200 | 0.2798 | 0.3225 |
75
+ | 0.0775 | 12.24 | 9600 | 0.2894 | 0.3224 |
76
+ | 0.0677 | 12.75 | 10000 | 0.2838 | 0.3204 |
77
+ | 0.1383 | 13.27 | 10400 | 0.2959 | 0.3211 |
78
+ | 0.1233 | 13.77 | 10800 | 0.2922 | 0.3213 |
79
+ | 0.0688 | 14.29 | 11200 | 0.2903 | 0.3209 |
80
+ | 0.0655 | 14.8 | 11600 | 0.2868 | 0.3182 |
81
+ | 0.0449 | 15.31 | 12000 | 0.2959 | 0.3172 |
82
+ | 0.0421 | 15.82 | 12400 | 0.2966 | 0.3180 |
83
+ | 0.0858 | 16.33 | 12800 | 0.2941 | 0.3164 |
84
+ | 0.0859 | 16.84 | 13200 | 0.2980 | 0.3165 |
85
+ | 0.0561 | 17.35 | 13600 | 0.2965 | 0.3165 |
86
+ | 0.0506 | 17.86 | 14000 | 0.2935 | 0.3148 |
87
+ | 0.0312 | 18.37 | 14400 | 0.2964 | 0.3154 |
88
+ | 0.0403 | 18.88 | 14800 | 0.2967 | 0.3160 |
89
+ | 0.0924 | 19.39 | 15200 | 0.2955 | 0.3147 |
90
+ | 0.0585 | 19.9 | 15600 | 0.2965 | 0.3144 |
91
 
92
 
93
  ### Framework versions