metadata
tags:
- generated_from_trainer
datasets:
- librispeech_asr
model-index:
- name: ''
results: []
This model was trained from scratch on the librispeech_asr dataset. It achieves the following results on the evaluation set:
- Loss: 18.0808
- Wer: 1.0
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.1986 | 0.28 | 500 | 8.8308 | 1.0007 |
| 5.1211 | 0.56 | 1000 | 12.3407 | 1.0025 |
| 4.4472 | 0.84 | 1500 | 14.1840 | 1.0025 |
| 5.4118 | 1.12 | 2000 | 11.8314 | 1.0469 |
| 5.2992 | 1.4 | 2500 | 14.5952 | 1.0047 |
| 5.1043 | 1.68 | 3000 | 13.5353 | 1.0055 |
| 5.4595 | 1.96 | 3500 | 16.3452 | 1.0020 |
| 4.5259 | 2.24 | 4000 | 17.2874 | 1.0018 |
| 4.6534 | 2.52 | 4500 | 18.2703 | 1.0010 |
| 4.3052 | 2.8 | 5000 | 18.0808 | 1.0 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu113
- Datasets 1.18.3
- Tokenizers 0.11.0