Hugging Face's logo

DewiBrynJones
/
wav2vec2-xlsr-53-ft-btb-ccv-enc-cy

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
DewiBrynJones/banc-trawsgrifiadau-bangor-clean-with-ccv
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
DewiBrynJones commited on
Commit
39b2f20
•
1 Parent(s): e25a7c2

Model save

Browse files
Files changed (1) hide show
  1. README.md +161 -0
README.md ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-large-xlsr-53
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: wav2vec2-xlsr-53-ft-btb-ccv-enc-cy
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
+ # wav2vec2-xlsr-53-ft-btb-ccv-enc-cy
17
+
18
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4095
21
+ - Wer: 0.3271
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: 0.0003
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 500
47
+ - training_steps: 10000
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:------:|:-----:|:---------------:|:------:|
54
+ | No log | 0.0194 | 100 | 3.5475 | 1.0 |
55
+ | No log | 0.0387 | 200 | 3.0259 | 1.0 |
56
+ | No log | 0.0581 | 300 | 3.0887 | 1.0 |
57
+ | No log | 0.0774 | 400 | 2.3822 | 0.9972 |
58
+ | 4.0938 | 0.0968 | 500 | 1.4547 | 0.9020 |
59
+ | 4.0938 | 0.1161 | 600 | 1.2603 | 0.8510 |
60
+ | 4.0938 | 0.1355 | 700 | 1.0940 | 0.7655 |
61
+ | 4.0938 | 0.1549 | 800 | 1.0705 | 0.7602 |
62
+ | 4.0938 | 0.1742 | 900 | 0.9356 | 0.6973 |
63
+ | 1.0597 | 0.1936 | 1000 | 0.9104 | 0.6766 |
64
+ | 1.0597 | 0.2129 | 1100 | 0.8879 | 0.6570 |
65
+ | 1.0597 | 0.2323 | 1200 | 0.8595 | 0.6612 |
66
+ | 1.0597 | 0.2516 | 1300 | 0.8352 | 0.6075 |
67
+ | 1.0597 | 0.2710 | 1400 | 0.7912 | 0.6033 |
68
+ | 0.8484 | 0.2904 | 1500 | 0.7862 | 0.6067 |
69
+ | 0.8484 | 0.3097 | 1600 | 0.7790 | 0.6009 |
70
+ | 0.8484 | 0.3291 | 1700 | 0.7678 | 0.5629 |
71
+ | 0.8484 | 0.3484 | 1800 | 0.7515 | 0.5799 |
72
+ | 0.8484 | 0.3678 | 1900 | 0.7424 | 0.5859 |
73
+ | 0.764 | 0.3871 | 2000 | 0.7130 | 0.5521 |
74
+ | 0.764 | 0.4065 | 2100 | 0.7114 | 0.5408 |
75
+ | 0.764 | 0.4259 | 2200 | 0.7229 | 0.5577 |
76
+ | 0.764 | 0.4452 | 2300 | 0.6773 | 0.5160 |
77
+ | 0.764 | 0.4646 | 2400 | 0.6784 | 0.5178 |
78
+ | 0.6868 | 0.4839 | 2500 | 0.6720 | 0.5262 |
79
+ | 0.6868 | 0.5033 | 2600 | 0.6804 | 0.5337 |
80
+ | 0.6868 | 0.5226 | 2700 | 0.6599 | 0.5024 |
81
+ | 0.6868 | 0.5420 | 2800 | 0.6287 | 0.4902 |
82
+ | 0.6868 | 0.5614 | 2900 | 0.6304 | 0.4947 |
83
+ | 0.6761 | 0.5807 | 3000 | 0.6258 | 0.4851 |
84
+ | 0.6761 | 0.6001 | 3100 | 0.6311 | 0.4990 |
85
+ | 0.6761 | 0.6194 | 3200 | 0.6172 | 0.4901 |
86
+ | 0.6761 | 0.6388 | 3300 | 0.6187 | 0.4666 |
87
+ | 0.6761 | 0.6581 | 3400 | 0.6045 | 0.4725 |
88
+ | 0.6462 | 0.6775 | 3500 | 0.5950 | 0.4717 |
89
+ | 0.6462 | 0.6969 | 3600 | 0.5903 | 0.4602 |
90
+ | 0.6462 | 0.7162 | 3700 | 0.5865 | 0.4727 |
91
+ | 0.6462 | 0.7356 | 3800 | 0.5820 | 0.4590 |
92
+ | 0.6462 | 0.7549 | 3900 | 0.6026 | 0.4830 |
93
+ | 0.6193 | 0.7743 | 4000 | 0.5807 | 0.4496 |
94
+ | 0.6193 | 0.7937 | 4100 | 0.5621 | 0.4486 |
95
+ | 0.6193 | 0.8130 | 4200 | 0.5730 | 0.4593 |
96
+ | 0.6193 | 0.8324 | 4300 | 0.5592 | 0.4374 |
97
+ | 0.6193 | 0.8517 | 4400 | 0.5621 | 0.4239 |
98
+ | 0.59 | 0.8711 | 4500 | 0.5458 | 0.4304 |
99
+ | 0.59 | 0.8904 | 4600 | 0.5406 | 0.4271 |
100
+ | 0.59 | 0.9098 | 4700 | 0.5269 | 0.4132 |
101
+ | 0.59 | 0.9292 | 4800 | 0.5362 | 0.4215 |
102
+ | 0.59 | 0.9485 | 4900 | 0.5226 | 0.4163 |
103
+ | 0.5636 | 0.9679 | 5000 | 0.5297 | 0.4148 |
104
+ | 0.5636 | 0.9872 | 5100 | 0.5226 | 0.4136 |
105
+ | 0.5636 | 1.0066 | 5200 | 0.5239 | 0.4054 |
106
+ | 0.5636 | 1.0259 | 5300 | 0.5383 | 0.4058 |
107
+ | 0.5636 | 1.0453 | 5400 | 0.5125 | 0.4067 |
108
+ | 0.4924 | 1.0647 | 5500 | 0.5029 | 0.3953 |
109
+ | 0.4924 | 1.0840 | 5600 | 0.5054 | 0.3932 |
110
+ | 0.4924 | 1.1034 | 5700 | 0.4969 | 0.3894 |
111
+ | 0.4924 | 1.1227 | 5800 | 0.4935 | 0.3851 |
112
+ | 0.4924 | 1.1421 | 5900 | 0.4977 | 0.3817 |
113
+ | 0.4602 | 1.1614 | 6000 | 0.4863 | 0.3874 |
114
+ | 0.4602 | 1.1808 | 6100 | 0.4906 | 0.3777 |
115
+ | 0.4602 | 1.2002 | 6200 | 0.4891 | 0.3764 |
116
+ | 0.4602 | 1.2195 | 6300 | 0.4881 | 0.3801 |
117
+ | 0.4602 | 1.2389 | 6400 | 0.4814 | 0.3727 |
118
+ | 0.4407 | 1.2582 | 6500 | 0.4714 | 0.3772 |
119
+ | 0.4407 | 1.2776 | 6600 | 0.4739 | 0.3706 |
120
+ | 0.4407 | 1.2969 | 6700 | 0.4692 | 0.3714 |
121
+ | 0.4407 | 1.3163 | 6800 | 0.4673 | 0.3728 |
122
+ | 0.4407 | 1.3357 | 6900 | 0.4610 | 0.3678 |
123
+ | 0.4284 | 1.3550 | 7000 | 0.4730 | 0.3653 |
124
+ | 0.4284 | 1.3744 | 7100 | 0.4606 | 0.3640 |
125
+ | 0.4284 | 1.3937 | 7200 | 0.4572 | 0.3620 |
126
+ | 0.4284 | 1.4131 | 7300 | 0.4575 | 0.3630 |
127
+ | 0.4284 | 1.4324 | 7400 | 0.4578 | 0.3590 |
128
+ | 0.4299 | 1.4518 | 7500 | 0.4477 | 0.3569 |
129
+ | 0.4299 | 1.4712 | 7600 | 0.4442 | 0.3552 |
130
+ | 0.4299 | 1.4905 | 7700 | 0.4420 | 0.3546 |
131
+ | 0.4299 | 1.5099 | 7800 | 0.4437 | 0.3483 |
132
+ | 0.4299 | 1.5292 | 7900 | 0.4373 | 0.3486 |
133
+ | 0.408 | 1.5486 | 8000 | 0.4336 | 0.3464 |
134
+ | 0.408 | 1.5679 | 8100 | 0.4348 | 0.3448 |
135
+ | 0.408 | 1.5873 | 8200 | 0.4276 | 0.3418 |
136
+ | 0.408 | 1.6067 | 8300 | 0.4294 | 0.3399 |
137
+ | 0.408 | 1.6260 | 8400 | 0.4272 | 0.3388 |
138
+ | 0.3964 | 1.6454 | 8500 | 0.4311 | 0.3409 |
139
+ | 0.3964 | 1.6647 | 8600 | 0.4260 | 0.3381 |
140
+ | 0.3964 | 1.6841 | 8700 | 0.4260 | 0.3371 |
141
+ | 0.3964 | 1.7034 | 8800 | 0.4260 | 0.3364 |
142
+ | 0.3964 | 1.7228 | 8900 | 0.4215 | 0.3351 |
143
+ | 0.3866 | 1.7422 | 9000 | 0.4234 | 0.3330 |
144
+ | 0.3866 | 1.7615 | 9100 | 0.4210 | 0.3319 |
145
+ | 0.3866 | 1.7809 | 9200 | 0.4156 | 0.3301 |
146
+ | 0.3866 | 1.8002 | 9300 | 0.4158 | 0.3303 |
147
+ | 0.3866 | 1.8196 | 9400 | 0.4155 | 0.3294 |
148
+ | 0.37 | 1.8389 | 9500 | 0.4137 | 0.3292 |
149
+ | 0.37 | 1.8583 | 9600 | 0.4120 | 0.3284 |
150
+ | 0.37 | 1.8777 | 9700 | 0.4109 | 0.3301 |
151
+ | 0.37 | 1.8970 | 9800 | 0.4100 | 0.3279 |
152
+ | 0.37 | 1.9164 | 9900 | 0.4095 | 0.3267 |
153
+ | 0.371 | 1.9357 | 10000 | 0.4095 | 0.3271 |
154
+
155
+
156
+ ### Framework versions
157
+
158
+ - Transformers 4.41.2
159
+ - Pytorch 2.3.1+cu121
160
+ - Datasets 2.20.0
161
+ - Tokenizers 0.19.1