<!-- 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_960_test
This model is a fine-tuned version of facebook/wav2vec2-base-960h on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1543
- Wer: 0.2187
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: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
6.3651 | 1.0 | 500 | 3.1433 | 1.0 |
1.7322 | 2.01 | 1000 | 0.3008 | 0.2972 |
0.5485 | 3.01 | 1500 | 0.2192 | 0.2632 |
0.4552 | 4.02 | 2000 | 0.2189 | 0.2621 |
0.3214 | 5.02 | 2500 | 0.1849 | 0.2454 |
0.264 | 6.02 | 3000 | 0.1886 | 0.2320 |
0.2718 | 7.03 | 3500 | 0.1776 | 0.2320 |
0.1725 | 8.03 | 4000 | 0.1674 | 0.2254 |
0.1656 | 9.04 | 4500 | 0.1543 | 0.2187 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.13.1+cu116
- Datasets 1.18.3
- Tokenizers 0.13.2