metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-base-timit-demo-colab
results: []
wav2vec2-base-timit-demo-colab
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: 0.4749
- Wer: 0.3444
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: 32
- 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: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.4101 | 4.0 | 500 | 1.2556 | 0.8153 |
| 0.5754 | 8.0 | 1000 | 0.4622 | 0.4482 |
| 0.2285 | 12.0 | 1500 | 0.4479 | 0.3860 |
| 0.1342 | 16.0 | 2000 | 0.4714 | 0.3652 |
| 0.0871 | 20.0 | 2500 | 0.4859 | 0.3581 |
| 0.0644 | 24.0 | 3000 | 0.4489 | 0.3485 |
| 0.0485 | 28.0 | 3500 | 0.4749 | 0.3444 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 1.18.3
- Tokenizers 0.15.0