metadata
license: apache-2.0
tags:
- audio-classification
- generated_from_trainer
datasets:
- superb
metrics:
- accuracy
model-index:
- name: speechcommand-demo
results: []
speechcommand-demo
This model is a fine-tuned version of facebook/wav2vec2-base on the superb dataset. It achieves the following results on the evaluation set:
- Loss: 0.0873
- Accuracy: 0.9809
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: 32
- eval_batch_size: 32
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6433 | 1.0 | 399 | 0.4979 | 0.9112 |
| 0.2406 | 2.0 | 798 | 0.1455 | 0.9750 |
| 0.1563 | 3.0 | 1197 | 0.1032 | 0.9785 |
| 0.1144 | 4.0 | 1597 | 0.0919 | 0.9806 |
| 0.1254 | 5.0 | 1995 | 0.0873 | 0.9809 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3