metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ipad-sample
results: []
ipad-sample
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5112
- Accuracy: 0.8636
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6909 | 1.0 | 6 | 0.7388 | 0.1818 |
| 0.6666 | 2.0 | 12 | 0.8264 | 0.1818 |
| 0.6935 | 3.0 | 18 | 0.8029 | 0.1818 |
| 0.5943 | 4.0 | 24 | 0.7576 | 0.1818 |
| 0.5859 | 5.0 | 30 | 0.6853 | 0.5 |
| 0.5545 | 6.0 | 36 | 0.6266 | 0.6818 |
| 0.511 | 7.0 | 42 | 0.5796 | 0.7273 |
| 0.4533 | 8.0 | 48 | 0.5119 | 0.7273 |
| 0.4505 | 9.0 | 54 | 0.4820 | 0.8636 |
| 0.3853 | 10.0 | 60 | 0.5112 | 0.8636 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2