metadata
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-base-timit-demo-google-colab
results: []
wav2vec2-base-timit-demo-google-colab
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6025
- Wer: 0.4421
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: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.8753 | 3.05 | 500 | 2.1566 | 0.9599 |
| 1.3505 | 6.1 | 1000 | 0.7121 | 0.6287 |
| 0.7278 | 9.15 | 1500 | 0.5651 | 0.5202 |
| 0.5178 | 12.2 | 2000 | 0.5785 | 0.4942 |
| 0.3887 | 15.24 | 2500 | 0.5684 | 0.4723 |
| 0.3194 | 18.29 | 3000 | 0.5718 | 0.4635 |
| 0.2873 | 21.34 | 3500 | 0.5871 | 0.4552 |
| 0.24 | 24.39 | 4000 | 0.6020 | 0.4501 |
| 0.2151 | 27.44 | 4500 | 0.6025 | 0.4421 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2