wav2vec2-xlsr-53-espeak-cv-ft-bak2-ntsema-colab
This model is a fine-tuned version of ntsema/wav2vec2-xlsr-53-espeak-cv-ft-tat-ntsema-colab on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: inf
- Wer: 1.0778
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: 0.0003
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1586 | 8.33 | 400 | inf | 1.0029 |
| 0.3107 | 16.66 | 800 | inf | 1.0202 |
| 0.1534 | 24.99 | 1200 | inf | 1.0778 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2