Commit
•
99cf47b
1
Parent(s):
af34bfa
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- common_voice_11_0
|
| 6 |
+
metrics:
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: wavlm-common_voice-ur
|
| 10 |
+
results:
|
| 11 |
+
- task:
|
| 12 |
+
name: Automatic Speech Recognition
|
| 13 |
+
type: automatic-speech-recognition
|
| 14 |
+
dataset:
|
| 15 |
+
name: common_voice_11_0
|
| 16 |
+
type: common_voice_11_0
|
| 17 |
+
config: ur
|
| 18 |
+
split: test
|
| 19 |
+
args: ur
|
| 20 |
+
metrics:
|
| 21 |
+
- name: Wer
|
| 22 |
+
type: wer
|
| 23 |
+
value: 0.37960668937751624
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 27 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 28 |
+
|
| 29 |
+
# wavlm-common_voice-ur
|
| 30 |
+
|
| 31 |
+
This model is a fine-tuned version of [microsoft/wavlm-large](https://huggingface.co/microsoft/wavlm-large) on the common_voice_11_0 dataset.
|
| 32 |
+
It achieves the following results on the evaluation set:
|
| 33 |
+
- Loss: inf
|
| 34 |
+
- Wer: 0.3796
|
| 35 |
+
|
| 36 |
+
## Model description
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Intended uses & limitations
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training and evaluation data
|
| 45 |
+
|
| 46 |
+
More information needed
|
| 47 |
+
|
| 48 |
+
## Training procedure
|
| 49 |
+
|
| 50 |
+
### Training hyperparameters
|
| 51 |
+
|
| 52 |
+
The following hyperparameters were used during training:
|
| 53 |
+
- learning_rate: 0.0003
|
| 54 |
+
- train_batch_size: 4
|
| 55 |
+
- eval_batch_size: 8
|
| 56 |
+
- seed: 42
|
| 57 |
+
- distributed_type: multi-GPU
|
| 58 |
+
- num_devices: 2
|
| 59 |
+
- total_train_batch_size: 8
|
| 60 |
+
- total_eval_batch_size: 16
|
| 61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- lr_scheduler_warmup_steps: 500
|
| 64 |
+
- num_epochs: 15.0
|
| 65 |
+
- mixed_precision_training: Native AMP
|
| 66 |
+
|
| 67 |
+
### Training results
|
| 68 |
+
|
| 69 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 70 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 71 |
+
| 4.9073 | 0.11 | 100 | inf | 1.0 |
|
| 72 |
+
| 3.3187 | 0.22 | 200 | inf | 1.0 |
|
| 73 |
+
| 2.9683 | 0.32 | 300 | inf | 0.9991 |
|
| 74 |
+
| 2.454 | 0.43 | 400 | inf | 0.9915 |
|
| 75 |
+
| 1.1169 | 0.54 | 500 | inf | 0.7906 |
|
| 76 |
+
| 1.5943 | 0.65 | 600 | inf | 0.7260 |
|
| 77 |
+
| 0.9991 | 0.75 | 700 | inf | 0.7305 |
|
| 78 |
+
| 1.0608 | 0.86 | 800 | inf | 0.6655 |
|
| 79 |
+
| 1.4739 | 0.97 | 900 | inf | 0.6120 |
|
| 80 |
+
| 0.8682 | 1.08 | 1000 | inf | 0.6087 |
|
| 81 |
+
| 0.8025 | 1.18 | 1100 | inf | 0.5991 |
|
| 82 |
+
| 0.8468 | 1.29 | 1200 | inf | 0.5605 |
|
| 83 |
+
| 0.5896 | 1.4 | 1300 | inf | 0.5550 |
|
| 84 |
+
| 0.6304 | 1.51 | 1400 | inf | 0.5441 |
|
| 85 |
+
| 0.6533 | 1.61 | 1500 | inf | 0.5297 |
|
| 86 |
+
| 0.7636 | 1.72 | 1600 | inf | 0.5210 |
|
| 87 |
+
| 0.5155 | 1.83 | 1700 | inf | 0.5331 |
|
| 88 |
+
| 0.6266 | 1.94 | 1800 | inf | 0.5182 |
|
| 89 |
+
| 0.4286 | 2.05 | 1900 | inf | 0.4956 |
|
| 90 |
+
| 0.527 | 2.15 | 2000 | inf | 0.4935 |
|
| 91 |
+
| 0.4919 | 2.26 | 2100 | inf | 0.4933 |
|
| 92 |
+
| 0.3977 | 2.37 | 2200 | inf | 0.5015 |
|
| 93 |
+
| 0.5349 | 2.48 | 2300 | inf | 0.4942 |
|
| 94 |
+
| 0.5066 | 2.58 | 2400 | inf | 0.4684 |
|
| 95 |
+
| 0.6734 | 2.69 | 2500 | inf | 0.4870 |
|
| 96 |
+
| 0.5411 | 2.8 | 2600 | inf | 0.4919 |
|
| 97 |
+
| 0.3451 | 2.91 | 2700 | inf | 0.4607 |
|
| 98 |
+
| 0.3913 | 3.01 | 2800 | inf | 0.4558 |
|
| 99 |
+
| 0.3046 | 3.12 | 2900 | inf | 0.4685 |
|
| 100 |
+
| 0.2954 | 3.23 | 3000 | inf | 0.4638 |
|
| 101 |
+
| 0.5469 | 3.34 | 3100 | inf | 0.4495 |
|
| 102 |
+
| 0.2334 | 3.44 | 3200 | inf | 0.4547 |
|
| 103 |
+
| 0.3119 | 3.55 | 3300 | inf | 0.4619 |
|
| 104 |
+
| 0.6393 | 3.66 | 3400 | inf | 0.4541 |
|
| 105 |
+
| 0.4133 | 3.77 | 3500 | inf | 0.4456 |
|
| 106 |
+
| 0.4946 | 3.88 | 3600 | inf | 0.4369 |
|
| 107 |
+
| 0.3484 | 3.98 | 3700 | inf | 0.4335 |
|
| 108 |
+
| 0.3996 | 4.09 | 3800 | inf | 0.4717 |
|
| 109 |
+
| 0.2754 | 4.2 | 3900 | inf | 0.4414 |
|
| 110 |
+
| 0.3141 | 4.31 | 4000 | inf | 0.4390 |
|
| 111 |
+
| 0.2231 | 4.41 | 4100 | inf | 0.4353 |
|
| 112 |
+
| 0.2673 | 4.52 | 4200 | inf | 0.4410 |
|
| 113 |
+
| 0.2911 | 4.63 | 4300 | inf | 0.4337 |
|
| 114 |
+
| 0.3643 | 4.74 | 4400 | inf | 0.4362 |
|
| 115 |
+
| 0.2706 | 4.84 | 4500 | inf | 0.4359 |
|
| 116 |
+
| 0.2464 | 4.95 | 4600 | inf | 0.4249 |
|
| 117 |
+
| 0.1453 | 5.06 | 4700 | inf | 0.4293 |
|
| 118 |
+
| 0.2619 | 5.17 | 4800 | inf | 0.4201 |
|
| 119 |
+
| 0.1888 | 5.27 | 4900 | inf | 0.4222 |
|
| 120 |
+
| 0.2571 | 5.38 | 5000 | inf | 0.4333 |
|
| 121 |
+
| 0.1653 | 5.49 | 5100 | inf | 0.4192 |
|
| 122 |
+
| 0.2102 | 5.6 | 5200 | inf | 0.4232 |
|
| 123 |
+
| 0.1456 | 5.71 | 5300 | inf | 0.4198 |
|
| 124 |
+
| 0.3314 | 5.81 | 5400 | inf | 0.4169 |
|
| 125 |
+
| 0.1703 | 5.92 | 5500 | inf | 0.4118 |
|
| 126 |
+
| 0.1546 | 6.03 | 5600 | inf | 0.4147 |
|
| 127 |
+
| 0.2065 | 6.14 | 5700 | inf | 0.4291 |
|
| 128 |
+
| 0.1792 | 6.24 | 5800 | inf | 0.4175 |
|
| 129 |
+
| 0.2433 | 6.35 | 5900 | inf | 0.4157 |
|
| 130 |
+
| 0.352 | 6.46 | 6000 | inf | 0.4083 |
|
| 131 |
+
| 0.2406 | 6.57 | 6100 | inf | 0.4341 |
|
| 132 |
+
| 0.2397 | 6.67 | 6200 | inf | 0.4185 |
|
| 133 |
+
| 0.2145 | 6.78 | 6300 | inf | 0.4147 |
|
| 134 |
+
| 0.1733 | 6.89 | 6400 | inf | 0.4150 |
|
| 135 |
+
| 0.1867 | 7.0 | 6500 | inf | 0.4154 |
|
| 136 |
+
| 0.612 | 7.1 | 6600 | inf | 0.4159 |
|
| 137 |
+
| 0.1413 | 7.21 | 6700 | inf | 0.4162 |
|
| 138 |
+
| 0.2074 | 7.32 | 6800 | inf | 0.4146 |
|
| 139 |
+
| 0.1362 | 7.43 | 6900 | inf | 0.4087 |
|
| 140 |
+
| 0.2971 | 7.53 | 7000 | inf | 0.4061 |
|
| 141 |
+
| 0.1443 | 7.64 | 7100 | inf | 0.4132 |
|
| 142 |
+
| 0.3066 | 7.75 | 7200 | inf | 0.4059 |
|
| 143 |
+
| 0.2163 | 7.86 | 7300 | inf | 0.4026 |
|
| 144 |
+
| 0.1251 | 7.97 | 7400 | inf | 0.4022 |
|
| 145 |
+
| 0.154 | 8.07 | 7500 | inf | 0.3980 |
|
| 146 |
+
| 0.1809 | 8.18 | 7600 | inf | 0.4030 |
|
| 147 |
+
| 0.0985 | 8.29 | 7700 | inf | 0.3992 |
|
| 148 |
+
| 0.1672 | 8.4 | 7800 | inf | 0.4049 |
|
| 149 |
+
| 0.1508 | 8.5 | 7900 | inf | 0.3985 |
|
| 150 |
+
| 0.1893 | 8.61 | 8000 | inf | 0.3999 |
|
| 151 |
+
| 0.1045 | 8.72 | 8100 | inf | 0.4014 |
|
| 152 |
+
| 0.2569 | 8.83 | 8200 | inf | 0.3976 |
|
| 153 |
+
| 0.2654 | 8.93 | 8300 | inf | 0.4021 |
|
| 154 |
+
| 0.0641 | 9.04 | 8400 | inf | 0.3964 |
|
| 155 |
+
| 0.1145 | 9.15 | 8500 | inf | 0.3995 |
|
| 156 |
+
| 0.1808 | 9.26 | 8600 | inf | 0.3960 |
|
| 157 |
+
| 0.0766 | 9.36 | 8700 | inf | 0.3938 |
|
| 158 |
+
| 0.1537 | 9.47 | 8800 | inf | 0.3909 |
|
| 159 |
+
| 0.2864 | 9.58 | 8900 | inf | 0.4028 |
|
| 160 |
+
| 0.1372 | 9.69 | 9000 | inf | 0.3970 |
|
| 161 |
+
| 0.06 | 9.8 | 9100 | inf | 0.3911 |
|
| 162 |
+
| 0.0831 | 9.9 | 9200 | inf | 0.3954 |
|
| 163 |
+
| 0.1469 | 10.01 | 9300 | inf | 0.3952 |
|
| 164 |
+
| 0.0683 | 10.12 | 9400 | inf | 0.3899 |
|
| 165 |
+
| 0.0694 | 10.23 | 9500 | inf | 0.3918 |
|
| 166 |
+
| 0.0919 | 10.33 | 9600 | inf | 0.3895 |
|
| 167 |
+
| 0.1842 | 10.44 | 9700 | inf | 0.3945 |
|
| 168 |
+
| 0.0581 | 10.55 | 9800 | inf | 0.3979 |
|
| 169 |
+
| 0.1397 | 10.66 | 9900 | inf | 0.3911 |
|
| 170 |
+
| 0.0657 | 10.76 | 10000 | inf | 0.3886 |
|
| 171 |
+
| 0.1316 | 10.87 | 10100 | inf | 0.3877 |
|
| 172 |
+
| 0.1434 | 10.98 | 10200 | inf | 0.3858 |
|
| 173 |
+
| 0.05 | 11.09 | 10300 | inf | 0.3842 |
|
| 174 |
+
| 0.0565 | 11.19 | 10400 | inf | 0.3873 |
|
| 175 |
+
| 0.1696 | 11.3 | 10500 | inf | 0.3873 |
|
| 176 |
+
| 0.0819 | 11.41 | 10600 | inf | 0.3901 |
|
| 177 |
+
| 0.0631 | 11.52 | 10700 | inf | 0.3927 |
|
| 178 |
+
| 0.1276 | 11.63 | 10800 | inf | 0.3868 |
|
| 179 |
+
| 0.1002 | 11.73 | 10900 | inf | 0.3848 |
|
| 180 |
+
| 0.081 | 11.84 | 11000 | inf | 0.3873 |
|
| 181 |
+
| 0.1745 | 11.95 | 11100 | inf | 0.3895 |
|
| 182 |
+
| 0.097 | 12.06 | 11200 | inf | 0.4021 |
|
| 183 |
+
| 0.0875 | 12.16 | 11300 | inf | 0.3876 |
|
| 184 |
+
| 0.027 | 12.27 | 11400 | inf | 0.3873 |
|
| 185 |
+
| 0.0859 | 12.38 | 11500 | inf | 0.3863 |
|
| 186 |
+
| 0.1192 | 12.49 | 11600 | inf | 0.3799 |
|
| 187 |
+
| 0.1055 | 12.59 | 11700 | inf | 0.3795 |
|
| 188 |
+
| 0.0603 | 12.7 | 11800 | inf | 0.3785 |
|
| 189 |
+
| 0.111 | 12.81 | 11900 | inf | 0.3783 |
|
| 190 |
+
| 0.0313 | 12.92 | 12000 | inf | 0.3800 |
|
| 191 |
+
| 0.0241 | 13.02 | 12100 | inf | 0.3796 |
|
| 192 |
+
| 0.1072 | 13.13 | 12200 | inf | 0.3803 |
|
| 193 |
+
| 0.1758 | 13.24 | 12300 | inf | 0.3809 |
|
| 194 |
+
| 0.1334 | 13.35 | 12400 | inf | 0.3794 |
|
| 195 |
+
| 0.1372 | 13.46 | 12500 | inf | 0.3798 |
|
| 196 |
+
| 0.1919 | 13.56 | 12600 | inf | 0.3791 |
|
| 197 |
+
| 0.1753 | 13.67 | 12700 | inf | 0.3781 |
|
| 198 |
+
| 0.294 | 13.78 | 12800 | inf | 0.3788 |
|
| 199 |
+
| 0.3132 | 13.89 | 12900 | inf | 0.3786 |
|
| 200 |
+
| 0.0486 | 13.99 | 13000 | inf | 0.3778 |
|
| 201 |
+
| 0.1199 | 14.1 | 13100 | inf | 0.3777 |
|
| 202 |
+
| 0.0381 | 14.21 | 13200 | inf | 0.3808 |
|
| 203 |
+
| 0.0875 | 14.32 | 13300 | inf | 0.3795 |
|
| 204 |
+
| 0.0122 | 14.42 | 13400 | inf | 0.3797 |
|
| 205 |
+
| 0.1417 | 14.53 | 13500 | inf | 0.3780 |
|
| 206 |
+
| 0.1754 | 14.64 | 13600 | inf | 0.3788 |
|
| 207 |
+
| 0.0426 | 14.75 | 13700 | inf | 0.3780 |
|
| 208 |
+
| 0.0309 | 14.85 | 13800 | inf | 0.3787 |
|
| 209 |
+
| 0.1447 | 14.96 | 13900 | inf | 0.3796 |
|
| 210 |
+
|
| 211 |
+
|
| 212 |
+
### Framework versions
|
| 213 |
+
|
| 214 |
+
- Transformers 4.27.0.dev0
|
| 215 |
+
- Pytorch 1.13.1
|
| 216 |
+
- Datasets 2.8.0
|
| 217 |
+
- Tokenizers 0.13.2
|