Hugging Face's logo

Amiran13
/
wav2vec2-large-xlsr-georgian_v1

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Amiran13 commited on
Commit
8b9ea1e
·
1 Parent(s): f9a812d

Model save

Browse files
Files changed (3) hide show
  1. README.md +133 -8
  2. model.safetensors +1 -1
  3. runs/Nov25_06-42-29_1afcb4349619/events.out.tfevents.1700896129.1afcb4349619.4109.0 +0 -0
README.md CHANGED
@@ -3,6 +3,8 @@ license: apache-2.0
3
  base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: wav2vec2-large-xlsr-georgian_v1
8
  results: []
@@ -15,13 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - eval_loss: 0.1635
19
- - eval_wer: 0.3316
20
- - eval_runtime: 1030.7944
21
- - eval_samples_per_second: 11.262
22
- - eval_steps_per_second: 0.704
23
- - epoch: 15.31
24
- - step: 9400
25
 
26
  ## Model description
27
 
@@ -49,9 +46,137 @@ The following hyperparameters were used during training:
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
  - lr_scheduler_warmup_steps: 200
52
- - num_epochs: 16
53
  - mixed_precision_training: Native AMP
54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  ### Framework versions
56
 
57
  - Transformers 4.35.2
 
3
  base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - wer
8
  model-index:
9
  - name: wav2vec2-large-xlsr-georgian_v1
10
  results: []
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1085
21
+ - Wer: 0.2807
 
 
 
 
 
22
 
23
  ## Model description
24
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 200
49
+ - num_epochs: 20
50
  - mixed_precision_training: Native AMP
51
 
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
56
+ | 3.1412 | 0.16 | 100 | 3.0855 | 1.0 |
57
+ | 3.0569 | 0.33 | 200 | 3.0369 | 1.0 |
58
+ | 2.9625 | 0.49 | 300 | 2.9778 | 1.0 |
59
+ | 0.7715 | 0.65 | 400 | 0.5113 | 0.7185 |
60
+ | 0.4725 | 0.81 | 500 | 0.3072 | 0.5138 |
61
+ | 0.4103 | 0.98 | 600 | 0.2447 | 0.4337 |
62
+ | 0.2775 | 1.14 | 700 | 0.2055 | 0.3769 |
63
+ | 0.2554 | 1.3 | 800 | 0.1950 | 0.3603 |
64
+ | 0.263 | 1.46 | 900 | 0.1813 | 0.3372 |
65
+ | 0.2294 | 1.63 | 1000 | 0.1664 | 0.3132 |
66
+ | 0.2296 | 1.79 | 1100 | 0.1565 | 0.2962 |
67
+ | 0.2183 | 1.95 | 1200 | 0.1474 | 0.2986 |
68
+ | 0.1822 | 2.12 | 1300 | 0.1546 | 0.2811 |
69
+ | 0.1798 | 2.28 | 1400 | 0.1442 | 0.2811 |
70
+ | 0.179 | 2.44 | 1500 | 0.1411 | 0.2686 |
71
+ | 0.1593 | 2.6 | 1600 | 0.1408 | 0.2739 |
72
+ | 0.2652 | 2.77 | 1700 | 0.2074 | 0.4499 |
73
+ | 0.1834 | 2.93 | 1800 | 0.1570 | 0.3942 |
74
+ | 0.2015 | 3.09 | 1900 | 0.1516 | 0.3859 |
75
+ | 0.1696 | 3.26 | 2000 | 0.1452 | 0.3826 |
76
+ | 0.1782 | 3.42 | 2100 | 0.1413 | 0.3763 |
77
+ | 0.1636 | 3.58 | 2200 | 0.1350 | 0.3761 |
78
+ | 0.173 | 3.74 | 2300 | 0.1323 | 0.3622 |
79
+ | 0.1704 | 3.91 | 2400 | 0.1289 | 0.3644 |
80
+ | 0.1418 | 4.07 | 2500 | 0.1266 | 0.3481 |
81
+ | 0.1403 | 4.23 | 2600 | 0.1274 | 0.3482 |
82
+ | 0.1353 | 4.4 | 2700 | 0.1287 | 0.3489 |
83
+ | 0.1432 | 4.56 | 2800 | 0.1293 | 0.3532 |
84
+ | 0.1283 | 4.72 | 2900 | 0.1226 | 0.3416 |
85
+ | 0.1367 | 4.88 | 3000 | 0.1206 | 0.3426 |
86
+ | 0.1162 | 5.05 | 3100 | 0.1222 | 0.3394 |
87
+ | 0.1267 | 5.21 | 3200 | 0.1183 | 0.3313 |
88
+ | 0.1126 | 5.37 | 3300 | 0.1180 | 0.3299 |
89
+ | 0.1127 | 5.53 | 3400 | 0.1177 | 0.3305 |
90
+ | 0.1155 | 5.7 | 3500 | 0.1185 | 0.3317 |
91
+ | 0.1086 | 5.86 | 3600 | 0.1129 | 0.3227 |
92
+ | 0.1135 | 6.02 | 3700 | 0.1118 | 0.3266 |
93
+ | 0.1112 | 6.19 | 3800 | 0.1142 | 0.3228 |
94
+ | 0.0866 | 6.35 | 3900 | 0.1172 | 0.3284 |
95
+ | 0.1003 | 6.51 | 4000 | 0.1133 | 0.3244 |
96
+ | 0.4366 | 6.68 | 4100 | 0.2436 | 0.4587 |
97
+ | 0.1216 | 6.84 | 4200 | 0.1344 | 0.3386 |
98
+ | 0.1165 | 7.0 | 4300 | 0.1280 | 0.3324 |
99
+ | 0.131 | 7.17 | 4400 | 0.1252 | 0.3245 |
100
+ | 0.1407 | 7.33 | 4500 | 0.1234 | 0.3252 |
101
+ | 0.1394 | 7.49 | 4600 | 0.1208 | 0.3177 |
102
+ | 0.1449 | 7.65 | 4700 | 0.1180 | 0.3165 |
103
+ | 0.1295 | 7.82 | 4800 | 0.1170 | 0.3152 |
104
+ | 0.1228 | 7.98 | 4900 | 0.1182 | 0.3160 |
105
+ | 0.0913 | 8.14 | 5000 | 0.1122 | 0.3086 |
106
+ | 0.1014 | 8.3 | 5100 | 0.1118 | 0.3100 |
107
+ | 0.0861 | 8.47 | 5200 | 0.1126 | 0.3074 |
108
+ | 0.1442 | 8.63 | 5300 | 0.1373 | 0.3311 |
109
+ | 0.1054 | 8.79 | 5400 | 0.1225 | 0.3143 |
110
+ | 0.104 | 8.96 | 5500 | 0.1190 | 0.3157 |
111
+ | 0.0972 | 9.12 | 5600 | 0.1140 | 0.3076 |
112
+ | 0.0948 | 9.28 | 5700 | 0.1090 | 0.3067 |
113
+ | 0.1067 | 9.45 | 5800 | 0.1117 | 0.3074 |
114
+ | 0.0798 | 9.61 | 5900 | 0.1097 | 0.3040 |
115
+ | 0.089 | 9.77 | 6000 | 0.1049 | 0.3005 |
116
+ | 0.0829 | 9.93 | 6100 | 0.1056 | 0.3006 |
117
+ | 0.0687 | 10.1 | 6200 | 0.1102 | 0.3018 |
118
+ | 0.0844 | 10.26 | 6300 | 0.1056 | 0.2985 |
119
+ | 0.0862 | 10.42 | 6400 | 0.1073 | 0.2990 |
120
+ | 0.0936 | 10.58 | 6500 | 0.1049 | 0.2949 |
121
+ | 0.0821 | 10.75 | 6600 | 0.1053 | 0.2966 |
122
+ | 0.0797 | 10.91 | 6700 | 0.1043 | 0.2939 |
123
+ | 0.0802 | 11.07 | 6800 | 0.1057 | 0.2911 |
124
+ | 0.0895 | 11.24 | 6900 | 0.1029 | 0.2934 |
125
+ | 0.073 | 11.4 | 7000 | 0.1042 | 0.2897 |
126
+ | 0.0842 | 11.56 | 7100 | 0.1023 | 0.2902 |
127
+ | 0.0825 | 11.72 | 7200 | 0.1024 | 0.2911 |
128
+ | 0.0958 | 11.89 | 7300 | 0.1018 | 0.2888 |
129
+ | 0.0698 | 12.05 | 7400 | 0.1030 | 0.2883 |
130
+ | 0.0693 | 12.21 | 7500 | 0.1019 | 0.2872 |
131
+ | 0.0736 | 12.37 | 7600 | 0.1003 | 0.2871 |
132
+ | 0.0683 | 12.54 | 7700 | 0.1004 | 0.2865 |
133
+ | 0.0649 | 12.7 | 7800 | 0.1005 | 0.2835 |
134
+ | 0.0669 | 12.86 | 7900 | 0.0985 | 0.2846 |
135
+ | 0.069 | 13.03 | 8000 | 0.0999 | 0.2844 |
136
+ | 0.0674 | 13.19 | 8100 | 0.1002 | 0.2835 |
137
+ | 0.0695 | 13.35 | 8200 | 0.1013 | 0.2829 |
138
+ | 0.0578 | 13.51 | 8300 | 0.1019 | 0.2821 |
139
+ | 0.0614 | 13.68 | 8400 | 0.0978 | 0.2815 |
140
+ | 0.0554 | 13.84 | 8500 | 0.0984 | 0.2813 |
141
+ | 0.0763 | 14.0 | 8600 | 0.1001 | 0.2813 |
142
+ | 0.0877 | 14.16 | 8700 | 0.1000 | 0.2808 |
143
+ | 0.0882 | 14.33 | 8800 | 0.0979 | 0.2803 |
144
+ | 0.0864 | 14.49 | 8900 | 0.0981 | 0.2788 |
145
+ | 0.0828 | 14.65 | 9000 | 0.0975 | 0.2790 |
146
+ | 0.3052 | 14.82 | 9100 | 0.2150 | 0.4175 |
147
+ | 0.1478 | 14.98 | 9200 | 0.1325 | 0.3027 |
148
+ | 1.0386 | 15.15 | 9300 | 0.4375 | 0.6793 |
149
+ | 0.116 | 15.31 | 9400 | 0.1266 | 0.3042 |
150
+ | 0.1226 | 15.47 | 9500 | 0.1206 | 0.3000 |
151
+ | 0.0885 | 15.63 | 9600 | 0.1173 | 0.2958 |
152
+ | 0.091 | 15.8 | 9700 | 0.1145 | 0.2929 |
153
+ | 0.0886 | 15.96 | 9800 | 0.1112 | 0.2908 |
154
+ | 0.0783 | 16.12 | 9900 | 0.1075 | 0.2873 |
155
+ | 0.069 | 16.28 | 10000 | 0.1072 | 0.2876 |
156
+ | 0.0783 | 16.45 | 10100 | 0.1070 | 0.2876 |
157
+ | 0.0669 | 16.61 | 10200 | 0.1055 | 0.2848 |
158
+ | 0.072 | 16.77 | 10300 | 0.1043 | 0.2846 |
159
+ | 0.0721 | 16.94 | 10400 | 0.1020 | 0.2821 |
160
+ | 0.0694 | 17.1 | 10500 | 0.1047 | 0.2803 |
161
+ | 0.0574 | 17.26 | 10600 | 0.1053 | 0.2830 |
162
+ | 0.0578 | 17.42 | 10700 | 0.1042 | 0.2806 |
163
+ | 0.0663 | 17.59 | 10800 | 0.1035 | 0.2801 |
164
+ | 0.0615 | 17.75 | 10900 | 0.1025 | 0.2785 |
165
+ | 0.0706 | 17.91 | 11000 | 0.1028 | 0.2792 |
166
+ | 0.2373 | 18.08 | 11100 | 0.1686 | 0.3372 |
167
+ | 0.1137 | 18.24 | 11200 | 0.1202 | 0.2938 |
168
+ | 0.1008 | 18.4 | 11300 | 0.1143 | 0.2895 |
169
+ | 0.1004 | 18.57 | 11400 | 0.1127 | 0.2874 |
170
+ | 0.0874 | 18.73 | 11500 | 0.1108 | 0.2861 |
171
+ | 0.0926 | 18.89 | 11600 | 0.1108 | 0.2838 |
172
+ | 0.0703 | 19.05 | 11700 | 0.1101 | 0.2834 |
173
+ | 0.0893 | 19.22 | 11800 | 0.1097 | 0.2824 |
174
+ | 0.0681 | 19.38 | 11900 | 0.1099 | 0.2822 |
175
+ | 0.0668 | 19.54 | 12000 | 0.1086 | 0.2813 |
176
+ | 0.069 | 19.7 | 12100 | 0.1087 | 0.2810 |
177
+ | 0.0683 | 19.87 | 12200 | 0.1085 | 0.2807 |
178
+
179
+
180
  ### Framework versions
181
 
182
  - Transformers 4.35.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbcacb22bfd298c59357a81240e9768dfc4841da7dd7f44fc2dd6e0b86a49a9f
3
  size 1261975580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73798ba7f7122167f6fe474451eb5d43eb64d645b519274739b962cb33dfce3c
3
  size 1261975580
runs/Nov25_06-42-29_1afcb4349619/events.out.tfevents.1700896129.1afcb4349619.4109.0 CHANGED
Binary files a/runs/Nov25_06-42-29_1afcb4349619/events.out.tfevents.1700896129.1afcb4349619.4109.0 and b/runs/Nov25_06-42-29_1afcb4349619/events.out.tfevents.1700896129.1afcb4349619.4109.0 differ