metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
name: Waynehills-STT-doogie-server
Waynehills-STT-doogie-server
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.9322
- Wer: 1.0368
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.9017 | 0.51 | 100 | 3.9322 | 1.0368 |
| 1.9117 | 1.01 | 200 | 3.9322 | 1.0368 |
| 1.9099 | 1.52 | 300 | 3.9322 | 1.0368 |
| 1.8933 | 2.02 | 400 | 3.9322 | 1.0368 |
| 1.8659 | 2.53 | 500 | 3.9322 | 1.0368 |
| 1.936 | 3.03 | 600 | 3.9322 | 1.0368 |
| 1.8939 | 3.54 | 700 | 3.9322 | 1.0368 |
| 1.9037 | 4.04 | 800 | 3.9322 | 1.0368 |
| 1.9076 | 4.55 | 900 | 3.9322 | 1.0368 |
| 1.9136 | 5.05 | 1000 | 3.9322 | 1.0368 |
| 1.8875 | 5.56 | 1100 | 3.9322 | 1.0368 |
| 1.9003 | 6.06 | 1200 | 3.9322 | 1.0368 |
| 1.9138 | 6.57 | 1300 | 3.9322 | 1.0368 |
| 1.8942 | 7.07 | 1400 | 3.9322 | 1.0368 |
| 1.9035 | 7.58 | 1500 | 3.9322 | 1.0368 |
| 1.9076 | 8.08 | 1600 | 3.9322 | 1.0368 |
| 1.8997 | 8.59 | 1700 | 3.9322 | 1.0368 |
| 1.8958 | 9.09 | 1800 | 3.9322 | 1.0368 |
| 1.891 | 9.6 | 1900 | 3.9322 | 1.0368 |
| 1.9245 | 10.1 | 2000 | 3.9322 | 1.0368 |
| 1.9042 | 10.61 | 2100 | 3.9322 | 1.0368 |
| 1.9153 | 11.11 | 2200 | 3.9322 | 1.0368 |
| 1.892 | 11.62 | 2300 | 3.9322 | 1.0368 |
| 1.8937 | 12.12 | 2400 | 3.9322 | 1.0368 |
| 1.9036 | 12.63 | 2500 | 3.9322 | 1.0368 |
| 1.9162 | 13.13 | 2600 | 3.9322 | 1.0368 |
| 1.9014 | 13.64 | 2700 | 3.9322 | 1.0368 |
| 1.9083 | 14.14 | 2800 | 3.9322 | 1.0368 |
| 1.9003 | 14.65 | 2900 | 3.9322 | 1.0368 |
| 1.9015 | 15.15 | 3000 | 3.9322 | 1.0368 |
| 1.8851 | 15.66 | 3100 | 3.9322 | 1.0368 |
| 1.9062 | 16.16 | 3200 | 3.9322 | 1.0368 |
| 1.9279 | 16.67 | 3300 | 3.9322 | 1.0368 |
| 1.8795 | 17.17 | 3400 | 3.9322 | 1.0368 |
| 1.9126 | 17.68 | 3500 | 3.9322 | 1.0368 |
| 1.8688 | 18.18 | 3600 | 3.9322 | 1.0368 |
| 1.9234 | 18.69 | 3700 | 3.9322 | 1.0368 |
| 1.8872 | 19.19 | 3800 | 3.9322 | 1.0368 |
| 1.9096 | 19.7 | 3900 | 3.9322 | 1.0368 |
| 1.8854 | 20.2 | 4000 | 3.9322 | 1.0368 |
| 1.9168 | 20.71 | 4100 | 3.9322 | 1.0368 |
| 1.9145 | 21.21 | 4200 | 3.9322 | 1.0368 |
| 1.904 | 21.72 | 4300 | 3.9322 | 1.0368 |
| 1.8982 | 22.22 | 4400 | 3.9322 | 1.0368 |
| 1.8978 | 22.73 | 4500 | 3.9322 | 1.0368 |
| 1.9023 | 23.23 | 4600 | 3.9322 | 1.0368 |
| 1.8901 | 23.74 | 4700 | 3.9322 | 1.0368 |
| 1.9079 | 24.24 | 4800 | 3.9322 | 1.0368 |
| 1.8923 | 24.75 | 4900 | 3.9322 | 1.0368 |
| 1.9095 | 25.25 | 5000 | 3.9322 | 1.0368 |
| 1.909 | 25.76 | 5100 | 3.9322 | 1.0368 |
| 1.8871 | 26.26 | 5200 | 3.9322 | 1.0368 |
| 1.9046 | 26.77 | 5300 | 3.9322 | 1.0368 |
| 1.8877 | 27.27 | 5400 | 3.9322 | 1.0368 |
| 1.901 | 27.78 | 5500 | 3.9322 | 1.0368 |
| 1.9045 | 28.28 | 5600 | 3.9322 | 1.0368 |
| 1.907 | 28.79 | 5700 | 3.9322 | 1.0368 |
| 1.9075 | 29.29 | 5800 | 3.9322 | 1.0368 |
| 1.895 | 29.8 | 5900 | 3.9322 | 1.0368 |
Framework versions
- Transformers 4.12.5
- Pytorch 1.10.0+cu113
- Datasets 1.17.0
- Tokenizers 0.10.3