metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: PNP_dys_asr_960h
results: []
PNP_dys_asr_960h
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: 0.7169
- Wer: 1.4123
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 |
|---|---|---|---|---|
| 9.4668 | 1.63 | 500 | 2.6987 | 1.0226 |
| 2.0533 | 3.26 | 1000 | 1.0528 | 2.4236 |
| 0.4828 | 4.89 | 1500 | 0.7560 | 1.3358 |
| 0.1604 | 6.51 | 2000 | 0.7169 | 1.4123 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.13.1+cu116
- Datasets 1.18.3
- Tokenizers 0.13.2