<!-- 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-large-xls-r-1b-frisian-cv-13-elderly
This model is a fine-tuned version of greenw0lf/wav2vec2-large-xls-r-1b-frisian on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3100
- Wer: 0.2977
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: 8e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 80
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
7.3658 | 5.0 | 50 | 1.9244 | 0.9718 |
0.8028 | 10.0 | 100 | 0.2503 | 0.2848 |
0.5111 | 15.0 | 150 | 0.2351 | 0.2870 |
0.7741 | 20.0 | 200 | 0.2383 | 0.2955 |
0.9183 | 25.0 | 250 | 0.2522 | 0.2977 |
0.5903 | 30.0 | 300 | 0.2773 | 0.3035 |
0.3031 | 35.0 | 350 | 0.2857 | 0.3067 |
0.4772 | 40.0 | 400 | 0.3087 | 0.3089 |
0.619 | 45.0 | 450 | 0.2857 | 0.3071 |
0.5617 | 50.0 | 500 | 0.2914 | 0.3035 |
0.4333 | 55.0 | 550 | 0.3058 | 0.3044 |
0.4576 | 60.0 | 600 | 0.3192 | 0.3008 |
0.3573 | 65.0 | 650 | 0.3158 | 0.3053 |
0.5565 | 70.0 | 700 | 0.3092 | 0.3076 |
0.4619 | 75.0 | 750 | 0.3110 | 0.3008 |
0.2608 | 80.0 | 800 | 0.3100 | 0.2977 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.2