metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: test-base
results: []
test-base
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1445.1470
- Wer: 1.0
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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6920.0094 | 1.0 | 50 | 8437.0029 | 1.0711 |
| 4915.5925 | 2.0 | 100 | 3042.6738 | 1.0 |
| 2169.443 | 3.0 | 150 | 1845.2919 | 1.0 |
| 1729.4778 | 4.0 | 200 | 1625.1453 | 1.0 |
| 1533.998 | 5.0 | 250 | 1445.1470 | 1.0 |
Framework versions
- Transformers 4.24.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3