<!-- 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. -->
w2v2-ami
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: 0.8686
- Wer: 0.2861
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
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
5.6021 | 3.07 | 500 | 2.9176 | 0.9997 |
2.5006 | 6.13 | 1000 | 1.0535 | 0.3617 |
0.9926 | 9.2 | 1500 | 0.8614 | 0.3036 |
0.809 | 12.27 | 2000 | 0.8676 | 0.2921 |
0.73 | 15.34 | 2500 | 0.8190 | 0.2966 |
0.6658 | 18.4 | 3000 | 0.8707 | 0.2900 |
0.6295 | 21.47 | 3500 | 0.8660 | 0.2821 |
0.6089 | 24.54 | 4000 | 0.8767 | 0.2829 |
0.5974 | 27.61 | 4500 | 0.8686 | 0.2861 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.12.1+cu113
- Datasets 1.18.3
- Tokenizers 0.12.1