Hugging Face's logo

HarrisDePerceptron
/
xls-r-300m-ur-cv7

Automatic Speech Recognition
Transformers
PyTorch
Urdu
wav2vec2
mozilla-foundation/common_voice_7_0
generated_from_trainer
Inference Endpoints
Model card Files Community
HarrisDePerceptron commited on
Commit
1abf5fe
•
1 Parent(s): 12892d5

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +54 -130
README.md CHANGED
@@ -1,10 +1,6 @@
1
  ---
2
- language:
3
- - ur
4
  license: apache-2.0
5
  tags:
6
- - automatic-speech-recognition
7
- - mozilla-foundation/common_voice_7_0
8
  - generated_from_trainer
9
  datasets:
10
  - common_voice
@@ -18,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  #
20
 
21
- This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - UR dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 1.7564
24
  - Wer: 0.7201
25
 
26
  ## Model description
@@ -48,134 +44,62 @@ The following hyperparameters were used during training:
48
  - total_train_batch_size: 16
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
- - lr_scheduler_warmup_steps: 1000
52
- - num_epochs: 500.0
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | Wer |
58
- |:-------------:|:------:|:-----:|:---------------:|:------:|
59
- | 18.5133 | 4.17 | 100 | 12.0376 | 1.0 |
60
- | 7.9152 | 8.33 | 200 | 6.2406 | 1.0 |
61
- | 5.363 | 12.5 | 300 | 4.6649 | 1.0 |
62
- | 4.05 | 16.67 | 400 | 3.5798 | 1.0 |
63
- | 3.3467 | 20.83 | 500 | 3.1930 | 1.0 |
64
- | 3.1638 | 25.0 | 600 | 3.0984 | 1.0 |
65
- | 3.043 | 29.17 | 700 | 2.9707 | 0.9983 |
66
- | 2.9566 | 33.33 | 800 | 2.9296 | 1.0 |
67
- | 2.8994 | 37.5 | 900 | 2.8290 | 0.9983 |
68
- | 2.6469 | 41.67 | 1000 | 2.2443 | 0.9765 |
69
- | 2.1557 | 45.83 | 1100 | 1.5079 | 0.8204 |
70
- | 1.7524 | 50.0 | 1200 | 1.2472 | 0.7594 |
71
- | 1.54 | 54.17 | 1300 | 1.1612 | 0.7097 |
72
- | 1.3985 | 58.33 | 1400 | 1.1158 | 0.7358 |
73
- | 1.2869 | 62.5 | 1500 | 1.0454 | 0.6931 |
74
- | 1.1952 | 66.67 | 1600 | 1.0130 | 0.6853 |
75
- | 1.1022 | 70.83 | 1700 | 1.0176 | 0.6966 |
76
- | 1.0346 | 75.0 | 1800 | 1.0053 | 0.6818 |
77
- | 0.9707 | 79.17 | 1900 | 1.0224 | 0.6713 |
78
- | 0.917 | 83.33 | 2000 | 1.0383 | 0.6530 |
79
- | 0.8574 | 87.5 | 2100 | 1.0632 | 0.6757 |
80
- | 0.8021 | 91.67 | 2200 | 1.0126 | 0.6443 |
81
- | 0.7563 | 95.83 | 2300 | 1.0678 | 0.6713 |
82
- | 0.709 | 100.0 | 2400 | 1.0756 | 0.6757 |
83
- | 0.6775 | 104.17 | 2500 | 1.0397 | 0.6914 |
84
- | 0.6325 | 108.33 | 2600 | 1.0556 | 0.6513 |
85
- | 0.617 | 112.5 | 2700 | 1.1219 | 0.6922 |
86
- | 0.5801 | 116.67 | 2800 | 1.1125 | 0.6870 |
87
- | 0.5367 | 120.83 | 2900 | 1.1397 | 0.6565 |
88
- | 0.5132 | 125.0 | 3000 | 1.1678 | 0.7001 |
89
- | 0.4948 | 129.17 | 3100 | 1.1276 | 0.6643 |
90
- | 0.457 | 133.33 | 3200 | 1.1465 | 0.6792 |
91
- | 0.4538 | 137.5 | 3300 | 1.1435 | 0.6809 |
92
- | 0.4227 | 141.67 | 3400 | 1.1457 | 0.6600 |
93
- | 0.4083 | 145.83 | 3500 | 1.1793 | 0.6652 |
94
- | 0.3965 | 150.0 | 3600 | 1.2435 | 0.6879 |
95
- | 0.382 | 154.17 | 3700 | 1.2229 | 0.6827 |
96
- | 0.3452 | 158.33 | 3800 | 1.2297 | 0.6879 |
97
- | 0.3434 | 162.5 | 3900 | 1.2350 | 0.6888 |
98
- | 0.3276 | 166.67 | 4000 | 1.2186 | 0.6922 |
99
- | 0.3052 | 170.83 | 4100 | 1.2338 | 0.6870 |
100
- | 0.3025 | 175.0 | 4200 | 1.2724 | 0.7079 |
101
- | 0.2916 | 179.17 | 4300 | 1.2758 | 0.6975 |
102
- | 0.2709 | 183.33 | 4400 | 1.2726 | 0.6748 |
103
- | 0.2707 | 187.5 | 4500 | 1.2643 | 0.6957 |
104
- | 0.262 | 191.67 | 4600 | 1.3214 | 0.7132 |
105
- | 0.2453 | 195.83 | 4700 | 1.2953 | 0.6861 |
106
- | 0.248 | 200.0 | 4800 | 1.3622 | 0.6774 |
107
- | 0.2325 | 204.17 | 4900 | 1.3594 | 0.6835 |
108
- | 0.2124 | 208.33 | 5000 | 1.3367 | 0.6652 |
109
- | 0.2253 | 212.5 | 5100 | 1.4157 | 0.6879 |
110
- | 0.2059 | 216.67 | 5200 | 1.4360 | 0.7132 |
111
- | 0.1951 | 220.83 | 5300 | 1.4606 | 0.7158 |
112
- | 0.1861 | 225.0 | 5400 | 1.4695 | 0.7018 |
113
- | 0.1916 | 229.17 | 5500 | 1.4031 | 0.6739 |
114
- | 0.1822 | 233.33 | 5600 | 1.4426 | 0.6870 |
115
- | 0.1684 | 237.5 | 5700 | 1.4069 | 0.7053 |
116
- | 0.1719 | 241.67 | 5800 | 1.4766 | 0.6966 |
117
- | 0.1569 | 245.83 | 5900 | 1.4509 | 0.6931 |
118
- | 0.159 | 250.0 | 6000 | 1.4467 | 0.7097 |
119
- | 0.1476 | 254.17 | 6100 | 1.4617 | 0.6870 |
120
- | 0.1497 | 258.33 | 6200 | 1.4460 | 0.6844 |
121
- | 0.1446 | 262.5 | 6300 | 1.5557 | 0.7088 |
122
- | 0.1389 | 266.67 | 6400 | 1.4886 | 0.7140 |
123
- | 0.1331 | 270.83 | 6500 | 1.5526 | 0.7062 |
124
- | 0.1344 | 275.0 | 6600 | 1.5419 | 0.7027 |
125
- | 0.1198 | 279.17 | 6700 | 1.5641 | 0.7001 |
126
- | 0.1242 | 283.33 | 6800 | 1.5390 | 0.7062 |
127
- | 0.12 | 287.5 | 6900 | 1.5406 | 0.7105 |
128
- | 0.1096 | 291.67 | 7000 | 1.5737 | 0.6975 |
129
- | 0.113 | 295.83 | 7100 | 1.5495 | 0.7210 |
130
- | 0.108 | 300.0 | 7200 | 1.5375 | 0.6949 |
131
- | 0.1072 | 304.17 | 7300 | 1.5337 | 0.7010 |
132
- | 0.0979 | 308.33 | 7400 | 1.5927 | 0.7062 |
133
- | 0.0983 | 312.5 | 7500 | 1.5882 | 0.6844 |
134
- | 0.0977 | 316.67 | 7600 | 1.6189 | 0.6957 |
135
- | 0.0947 | 320.83 | 7700 | 1.5098 | 0.6818 |
136
- | 0.0996 | 325.0 | 7800 | 1.6269 | 0.7254 |
137
- | 0.0846 | 329.17 | 7900 | 1.6367 | 0.7088 |
138
- | 0.0953 | 333.33 | 8000 | 1.5965 | 0.7123 |
139
- | 0.0906 | 337.5 | 8100 | 1.6096 | 0.7123 |
140
- | 0.093 | 341.67 | 8200 | 1.5953 | 0.6983 |
141
- | 0.0784 | 345.83 | 8300 | 1.5884 | 0.6914 |
142
- | 0.0769 | 350.0 | 8400 | 1.5794 | 0.6870 |
143
- | 0.0782 | 354.17 | 8500 | 1.6581 | 0.6818 |
144
- | 0.0764 | 358.33 | 8600 | 1.6555 | 0.7088 |
145
- | 0.073 | 362.5 | 8700 | 1.6466 | 0.6931 |
146
- | 0.0703 | 366.67 | 8800 | 1.6615 | 0.7114 |
147
- | 0.0707 | 370.83 | 8900 | 1.6743 | 0.7079 |
148
- | 0.0647 | 375.0 | 9000 | 1.6452 | 0.7167 |
149
- | 0.0614 | 379.17 | 9100 | 1.7082 | 0.7123 |
150
- | 0.0646 | 383.33 | 9200 | 1.6848 | 0.7184 |
151
- | 0.0648 | 387.5 | 9300 | 1.6581 | 0.7088 |
152
- | 0.0625 | 391.67 | 9400 | 1.7315 | 0.7341 |
153
- | 0.0637 | 395.83 | 9500 | 1.6831 | 0.7027 |
154
- | 0.0558 | 400.0 | 9600 | 1.7159 | 0.7280 |
155
- | 0.0563 | 404.17 | 9700 | 1.7475 | 0.7158 |
156
- | 0.0568 | 408.33 | 9800 | 1.6776 | 0.6992 |
157
- | 0.0574 | 412.5 | 9900 | 1.7150 | 0.6983 |
158
- | 0.0561 | 416.67 | 10000 | 1.7315 | 0.7140 |
159
- | 0.0494 | 420.83 | 10100 | 1.6869 | 0.7219 |
160
- | 0.0495 | 425.0 | 10200 | 1.7500 | 0.7262 |
161
- | 0.0542 | 429.17 | 10300 | 1.7298 | 0.7271 |
162
- | 0.0509 | 433.33 | 10400 | 1.7334 | 0.7262 |
163
- | 0.046 | 437.5 | 10500 | 1.7048 | 0.7193 |
164
- | 0.0423 | 441.67 | 10600 | 1.7168 | 0.7193 |
165
- | 0.0477 | 445.83 | 10700 | 1.7388 | 0.7210 |
166
- | 0.0436 | 450.0 | 10800 | 1.7279 | 0.7167 |
167
- | 0.0466 | 454.17 | 10900 | 1.6968 | 0.7053 |
168
- | 0.0424 | 458.33 | 11000 | 1.7237 | 0.7184 |
169
- | 0.0447 | 462.5 | 11100 | 1.7218 | 0.7184 |
170
- | 0.0455 | 466.67 | 11200 | 1.7506 | 0.7219 |
171
- | 0.0446 | 470.83 | 11300 | 1.7542 | 0.7280 |
172
- | 0.043 | 475.0 | 11400 | 1.7501 | 0.7201 |
173
- | 0.0397 | 479.17 | 11500 | 1.7837 | 0.7245 |
174
- | 0.0402 | 483.33 | 11600 | 1.7762 | 0.7175 |
175
- | 0.039 | 487.5 | 11700 | 1.7771 | 0.7262 |
176
- | 0.0402 | 491.67 | 11800 | 1.7564 | 0.7219 |
177
- | 0.0368 | 495.83 | 11900 | 1.7553 | 0.7193 |
178
- | 0.0395 | 500.0 | 12000 | 1.7564 | 0.7201 |
179
 
180
 
181
  ### Framework versions
 
1
  ---
 
 
2
  license: apache-2.0
3
  tags:
 
 
4
  - generated_from_trainer
5
  datasets:
6
  - common_voice
 
14
 
15
  #
16
 
17
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.2924
20
  - Wer: 0.7201
21
 
22
  ## Model description
 
44
  - total_train_batch_size: 16
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 100
48
+ - num_epochs: 200.0
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:------:|:----:|:---------------:|:------:|
55
+ | 11.2783 | 4.17 | 100 | 4.6409 | 1.0 |
56
+ | 3.5578 | 8.33 | 200 | 3.1649 | 1.0 |
57
+ | 3.1279 | 12.5 | 300 | 3.0335 | 1.0 |
58
+ | 2.9944 | 16.67 | 400 | 2.9526 | 0.9983 |
59
+ | 2.9275 | 20.83 | 500 | 2.9291 | 1.0009 |
60
+ | 2.8077 | 25.0 | 600 | 2.5633 | 0.9895 |
61
+ | 2.4438 | 29.17 | 700 | 1.9045 | 0.9564 |
62
+ | 1.9659 | 33.33 | 800 | 1.4114 | 0.7960 |
63
+ | 1.7092 | 37.5 | 900 | 1.2584 | 0.7637 |
64
+ | 1.517 | 41.67 | 1000 | 1.2040 | 0.7507 |
65
+ | 1.3966 | 45.83 | 1100 | 1.1273 | 0.7463 |
66
+ | 1.3197 | 50.0 | 1200 | 1.1054 | 0.6957 |
67
+ | 1.2476 | 54.17 | 1300 | 1.1035 | 0.7001 |
68
+ | 1.1796 | 58.33 | 1400 | 1.0890 | 0.7097 |
69
+ | 1.1237 | 62.5 | 1500 | 1.0883 | 0.7167 |
70
+ | 1.0777 | 66.67 | 1600 | 1.1067 | 0.7219 |
71
+ | 1.0051 | 70.83 | 1700 | 1.1115 | 0.7236 |
72
+ | 0.9521 | 75.0 | 1800 | 1.0867 | 0.7132 |
73
+ | 0.9147 | 79.17 | 1900 | 1.0852 | 0.7210 |
74
+ | 0.8798 | 83.33 | 2000 | 1.1411 | 0.7097 |
75
+ | 0.8317 | 87.5 | 2100 | 1.1634 | 0.7018 |
76
+ | 0.7946 | 91.67 | 2200 | 1.1621 | 0.7201 |
77
+ | 0.7594 | 95.83 | 2300 | 1.1482 | 0.7036 |
78
+ | 0.729 | 100.0 | 2400 | 1.1493 | 0.7062 |
79
+ | 0.7055 | 104.17 | 2500 | 1.1726 | 0.6931 |
80
+ | 0.6622 | 108.33 | 2600 | 1.1938 | 0.7001 |
81
+ | 0.6583 | 112.5 | 2700 | 1.1832 | 0.7149 |
82
+ | 0.6299 | 116.67 | 2800 | 1.1996 | 0.7175 |
83
+ | 0.5903 | 120.83 | 2900 | 1.1986 | 0.7132 |
84
+ | 0.5816 | 125.0 | 3000 | 1.1909 | 0.7010 |
85
+ | 0.5583 | 129.17 | 3100 | 1.2079 | 0.6870 |
86
+ | 0.5392 | 133.33 | 3200 | 1.2109 | 0.7228 |
87
+ | 0.5412 | 137.5 | 3300 | 1.2353 | 0.7245 |
88
+ | 0.5136 | 141.67 | 3400 | 1.2390 | 0.7254 |
89
+ | 0.5007 | 145.83 | 3500 | 1.2273 | 0.7123 |
90
+ | 0.4883 | 150.0 | 3600 | 1.2773 | 0.7289 |
91
+ | 0.4835 | 154.17 | 3700 | 1.2678 | 0.7289 |
92
+ | 0.4568 | 158.33 | 3800 | 1.2592 | 0.7350 |
93
+ | 0.4525 | 162.5 | 3900 | 1.2705 | 0.7254 |
94
+ | 0.4379 | 166.67 | 4000 | 1.2717 | 0.7306 |
95
+ | 0.4198 | 170.83 | 4100 | 1.2618 | 0.7219 |
96
+ | 0.4216 | 175.0 | 4200 | 1.2909 | 0.7158 |
97
+ | 0.4305 | 179.17 | 4300 | 1.2808 | 0.7167 |
98
+ | 0.399 | 183.33 | 4400 | 1.2750 | 0.7193 |
99
+ | 0.3937 | 187.5 | 4500 | 1.2719 | 0.7149 |
100
+ | 0.3905 | 191.67 | 4600 | 1.2816 | 0.7158 |
101
+ | 0.3892 | 195.83 | 4700 | 1.2951 | 0.7210 |
102
+ | 0.3932 | 200.0 | 4800 | 1.2924 | 0.7201 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
103
 
104
 
105
  ### Framework versions