<!-- 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. -->
dys_asr_rub
This model is a fine-tuned version of facebook/wav2vec2-large-960h-lv60-self on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0257
- Wer: 0.9875
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: 7
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
12.3902 | 0.79 | 500 | 4.0453 | 1.0 |
1.8958 | 1.58 | 1000 | 0.4618 | 1.2804 |
0.3581 | 2.37 | 1500 | 0.1455 | 1.0498 |
0.1861 | 3.16 | 2000 | 0.1212 | 1.0156 |
0.108 | 3.95 | 2500 | 0.0211 | 0.9969 |
0.0719 | 4.74 | 3000 | 0.0574 | 0.9875 |
0.0768 | 5.53 | 3500 | 0.0313 | 0.9907 |
0.0547 | 6.32 | 4000 | 0.0257 | 0.9875 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.13.1+cu116
- Datasets 1.18.3
- Tokenizers 0.13.2