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: 0.4544
- Wer: 0.3391
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 |
|---|---|---|---|---|
| 3.4381 | 4.0 | 500 | 1.5173 | 0.9825 |
| 0.636 | 8.0 | 1000 | 0.4512 | 0.4526 |
| 0.2259 | 12.0 | 1500 | 0.4340 | 0.3933 |
| 0.1295 | 16.0 | 2000 | 0.4602 | 0.3809 |
| 0.0869 | 20.0 | 2500 | 0.4283 | 0.3553 |
| 0.0613 | 24.0 | 3000 | 0.4334 | 0.3443 |
| 0.0481 | 28.0 | 3500 | 0.4544 | 0.3391 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0+cu118
- Datasets 1.18.3
- Tokenizers 0.15.0