<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
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: 0.4627
- Wer: 0.3518
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 |
|---|---|---|---|---|
| 3.4716 | 4.0 | 500 | 1.3023 | 0.9254 |
| 0.5958 | 8.0 | 1000 | 0.4582 | 0.4399 |
| 0.2223 | 12.0 | 1500 | 0.4477 | 0.3886 |
| 0.1373 | 16.0 | 2000 | 0.4791 | 0.3630 |
| 0.101 | 20.0 | 2500 | 0.4676 | 0.3561 |
| 0.0724 | 24.0 | 3000 | 0.4539 | 0.3510 |
| 0.0513 | 28.0 | 3500 | 0.4627 | 0.3518 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 1.17.0
- Tokenizers 0.12.1
