<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
wav2vec2-base-torgo-demo-m04-nolm
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.5735
- Wer: 1.0
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: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.431 | 0.88 | 500 | 4.5567 | 1.0 |
| 3.4727 | 1.75 | 1000 | 3.5626 | 1.0 |
| 3.3879 | 2.63 | 1500 | 3.9274 | 1.0 |
| 3.3513 | 3.5 | 2000 | 3.4813 | 1.0 |
| 3.3538 | 4.38 | 2500 | 3.7300 | 1.0 |
| 3.3539 | 5.25 | 3000 | 3.5714 | 1.0 |
| 3.339 | 6.13 | 3500 | 3.6732 | 1.0 |
| 3.3038 | 7.01 | 4000 | 3.6788 | 1.0 |
| 3.35 | 7.88 | 4500 | 3.6715 | 1.0 |
| 3.338 | 8.76 | 5000 | 3.5161 | 1.0 |
| 3.3306 | 9.63 | 5500 | 3.7386 | 1.0 |
| 3.3266 | 10.51 | 6000 | 3.4908 | 1.0 |
| 3.3184 | 11.38 | 6500 | 3.7669 | 1.0 |
| 3.3189 | 12.26 | 7000 | 3.6142 | 1.0 |
| 3.331 | 13.13 | 7500 | 3.5619 | 1.0 |
| 3.3139 | 14.01 | 8000 | 3.6632 | 1.0 |
| 3.3069 | 14.89 | 8500 | 3.6127 | 1.0 |
| 3.315 | 15.76 | 9000 | 3.5562 | 1.0 |
| 3.3079 | 16.64 | 9500 | 3.7094 | 1.0 |
| 3.3077 | 17.51 | 10000 | 3.5412 | 1.0 |
| 3.3188 | 18.39 | 10500 | 3.6303 | 1.0 |
| 3.3133 | 19.26 | 11000 | 3.5704 | 1.0 |
| 3.3428 | 20.14 | 11500 | 3.5662 | 1.0 |
| 3.3082 | 21.02 | 12000 | 3.6084 | 1.0 |
| 3.3238 | 21.89 | 12500 | 3.6164 | 1.0 |
| 3.3119 | 22.77 | 13000 | 3.5787 | 1.0 |
| 3.2981 | 23.64 | 13500 | 3.6356 | 1.0 |
| 3.3153 | 24.52 | 14000 | 3.5726 | 1.0 |
| 3.3065 | 25.39 | 14500 | 3.5908 | 1.0 |
| 3.3199 | 26.27 | 15000 | 3.5823 | 1.0 |
| 3.306 | 27.15 | 15500 | 3.5658 | 1.0 |
| 3.3153 | 28.02 | 16000 | 3.5818 | 1.0 |
| 3.2762 | 28.9 | 16500 | 3.5810 | 1.0 |
| 3.3196 | 29.77 | 17000 | 3.5735 | 1.0 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.0.0
- Tokenizers 0.13.2
