Hugging Face's logo

Shawal777
/
nyankole_wav2vec2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Shawal777 commited on
Commit
47d6910
·
verified ·
1 Parent(s): 701441e

End of training

Browse files
Files changed (1) hide show
  1. README.md +70 -37
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.8615
21
  - Wer: 1.0
22
 
23
  ## Model description
@@ -38,14 +38,14 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.0003
41
- - train_batch_size: 4
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - gradient_accumulation_steps: 2
45
- - total_train_batch_size: 8
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - lr_scheduler_warmup_steps: 150
49
  - num_epochs: 30
50
  - mixed_precision_training: Native AMP
51
 
@@ -53,41 +53,74 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:-------:|:----:|:---------------:|:---:|
56
- | 2.9097 | 0.9976 | 210 | 2.9031 | 1.0 |
57
- | 2.8649 | 2.0 | 421 | 2.8534 | 1.0 |
58
- | 2.8545 | 2.9976 | 631 | 2.8537 | 1.0 |
59
- | 2.8465 | 4.0 | 842 | 2.8554 | 1.0 |
60
- | 2.8509 | 4.9976 | 1052 | 2.8629 | 1.0 |
61
- | 2.8491 | 6.0 | 1263 | 2.8828 | 1.0 |
62
- | 2.8463 | 6.9976 | 1473 | 2.8570 | 1.0 |
63
- | 2.8477 | 8.0 | 1684 | 2.8675 | 1.0 |
64
- | 2.8478 | 8.9976 | 1894 | 2.8605 | 1.0 |
65
- | 2.8411 | 10.0 | 2105 | 2.8593 | 1.0 |
66
- | 2.8493 | 10.9976 | 2315 | 2.8573 | 1.0 |
67
- | 2.8478 | 12.0 | 2526 | 2.8564 | 1.0 |
68
- | 2.8823 | 12.9976 | 2736 | 2.8538 | 1.0 |
69
- | 2.8413 | 14.0 | 2947 | 2.8534 | 1.0 |
70
- | 2.8497 | 14.9976 | 3157 | 2.8487 | 1.0 |
71
- | 2.8439 | 16.0 | 3368 | 2.8642 | 1.0 |
72
- | 2.8442 | 16.9976 | 3578 | 2.8527 | 1.0 |
73
- | 2.8425 | 18.0 | 3789 | 2.8611 | 1.0 |
74
- | 2.841 | 18.9976 | 3999 | 2.8617 | 1.0 |
75
- | 2.8426 | 20.0 | 4210 | 2.8563 | 1.0 |
76
- | 2.8454 | 20.9976 | 4420 | 2.8527 | 1.0 |
77
- | 2.8396 | 22.0 | 4631 | 2.8568 | 1.0 |
78
- | 2.8449 | 22.9976 | 4841 | 2.8503 | 1.0 |
79
- | 2.8424 | 24.0 | 5052 | 2.8596 | 1.0 |
80
- | 2.8438 | 24.9976 | 5262 | 2.8624 | 1.0 |
81
- | 2.8414 | 26.0 | 5473 | 2.8606 | 1.0 |
82
- | 2.8387 | 26.9976 | 5683 | 2.8635 | 1.0 |
83
- | 2.8408 | 28.0 | 5894 | 2.8569 | 1.0 |
84
- | 2.8729 | 28.9976 | 6104 | 2.8640 | 1.0 |
85
- | 2.8417 | 29.9287 | 6300 | 2.8615 | 1.0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
86
 
87
 
88
  ### Framework versions
89
 
90
- - Transformers 4.42.4
91
- - Pytorch 2.1.0+cu118
92
- - Datasets 2.20.0
93
  - Tokenizers 0.19.1
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.8606
21
  - Wer: 1.0
22
 
23
  ## Model description
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.0003
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: 55
49
  - num_epochs: 30
50
  - mixed_precision_training: Native AMP
51
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:-------:|:----:|:---------------:|:---:|
56
+ | 7.4272 | 0.4739 | 50 | 2.9131 | 1.0 |
57
+ | 2.8729 | 0.9479 | 100 | 2.8567 | 1.0 |
58
+ | 2.9027 | 1.4218 | 150 | 2.9014 | 1.0 |
59
+ | 2.8676 | 1.8957 | 200 | 2.8607 | 1.0 |
60
+ | 2.8484 | 2.3697 | 250 | 2.8482 | 1.0 |
61
+ | 2.8807 | 2.8436 | 300 | 2.8553 | 1.0 |
62
+ | 2.8513 | 3.3175 | 350 | 2.8731 | 1.0 |
63
+ | 2.8489 | 3.7915 | 400 | 2.8524 | 1.0 |
64
+ | 2.841 | 4.2654 | 450 | 2.8468 | 1.0 |
65
+ | 2.9182 | 4.7393 | 500 | 2.8572 | 1.0 |
66
+ | 2.8441 | 5.2133 | 550 | 2.8642 | 1.0 |
67
+ | 2.8486 | 5.6872 | 600 | 2.8690 | 1.0 |
68
+ | 2.8455 | 6.1611 | 650 | 2.8663 | 1.0 |
69
+ | 2.845 | 6.6351 | 700 | 2.8611 | 1.0 |
70
+ | 2.856 | 7.1090 | 750 | 2.8781 | 1.0 |
71
+ | 2.8429 | 7.5829 | 800 | 2.8612 | 1.0 |
72
+ | 2.8456 | 8.0569 | 850 | 2.8555 | 1.0 |
73
+ | 2.8465 | 8.5308 | 900 | 2.8596 | 1.0 |
74
+ | 2.8465 | 9.0047 | 950 | 2.8507 | 1.0 |
75
+ | 2.848 | 9.4787 | 1000 | 2.8527 | 1.0 |
76
+ | 2.8441 | 9.9526 | 1050 | 2.8702 | 1.0 |
77
+ | 2.8452 | 10.4265 | 1100 | 2.8782 | 1.0 |
78
+ | 2.8446 | 10.9005 | 1150 | 2.8736 | 1.0 |
79
+ | 2.8433 | 11.3744 | 1200 | 2.8541 | 1.0 |
80
+ | 2.842 | 11.8483 | 1250 | 2.8678 | 1.0 |
81
+ | 2.8442 | 12.3223 | 1300 | 2.8559 | 1.0 |
82
+ | 2.8473 | 12.7962 | 1350 | 2.8538 | 1.0 |
83
+ | 2.843 | 13.2701 | 1400 | 2.8592 | 1.0 |
84
+ | 2.8429 | 13.7441 | 1450 | 2.8571 | 1.0 |
85
+ | 2.8431 | 14.2180 | 1500 | 2.8860 | 1.0 |
86
+ | 2.8428 | 14.6919 | 1550 | 2.8611 | 1.0 |
87
+ | 2.8429 | 15.1659 | 1600 | 2.8763 | 1.0 |
88
+ | 2.8387 | 15.6398 | 1650 | 2.8637 | 1.0 |
89
+ | 2.8503 | 16.1137 | 1700 | 2.8588 | 1.0 |
90
+ | 2.8463 | 16.5877 | 1750 | 2.8560 | 1.0 |
91
+ | 2.8414 | 17.0616 | 1800 | 2.8550 | 1.0 |
92
+ | 2.8417 | 17.5355 | 1850 | 2.8582 | 1.0 |
93
+ | 2.8438 | 18.0095 | 1900 | 2.8502 | 1.0 |
94
+ | 2.8497 | 18.4834 | 1950 | 2.8825 | 1.0 |
95
+ | 2.8377 | 18.9573 | 2000 | 2.8622 | 1.0 |
96
+ | 2.8412 | 19.4313 | 2050 | 2.8711 | 1.0 |
97
+ | 2.8405 | 19.9052 | 2100 | 2.8786 | 1.0 |
98
+ | 2.8419 | 20.3791 | 2150 | 2.8467 | 1.0 |
99
+ | 2.8426 | 20.8531 | 2200 | 2.8627 | 1.0 |
100
+ | 2.8454 | 21.3270 | 2250 | 2.8640 | 1.0 |
101
+ | 2.8397 | 21.8009 | 2300 | 2.8600 | 1.0 |
102
+ | 2.8405 | 22.2749 | 2350 | 2.8716 | 1.0 |
103
+ | 2.8413 | 22.7488 | 2400 | 2.8498 | 1.0 |
104
+ | 2.8454 | 23.2227 | 2450 | 2.8647 | 1.0 |
105
+ | 2.8415 | 23.6967 | 2500 | 2.8727 | 1.0 |
106
+ | 2.8381 | 24.1706 | 2550 | 2.8600 | 1.0 |
107
+ | 2.8405 | 24.6445 | 2600 | 2.8604 | 1.0 |
108
+ | 2.8442 | 25.1185 | 2650 | 2.8543 | 1.0 |
109
+ | 2.836 | 25.5924 | 2700 | 2.8613 | 1.0 |
110
+ | 2.8479 | 26.0664 | 2750 | 2.8664 | 1.0 |
111
+ | 2.842 | 26.5403 | 2800 | 2.8574 | 1.0 |
112
+ | 2.8406 | 27.0142 | 2850 | 2.8558 | 1.0 |
113
+ | 2.8435 | 27.4882 | 2900 | 2.8587 | 1.0 |
114
+ | 2.8387 | 27.9621 | 2950 | 2.8568 | 1.0 |
115
+ | 2.8442 | 28.4360 | 3000 | 2.8573 | 1.0 |
116
+ | 2.8365 | 28.9100 | 3050 | 2.8591 | 1.0 |
117
+ | 2.8428 | 29.3839 | 3100 | 2.8621 | 1.0 |
118
+ | 2.8386 | 29.8578 | 3150 | 2.8606 | 1.0 |
119
 
120
 
121
  ### Framework versions
122
 
123
+ - Transformers 4.41.2
124
+ - Pytorch 2.1.2
125
+ - Datasets 2.19.2
126
  - Tokenizers 0.19.1