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: 6.9553
- Wer: 2.0097
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 |
|---|---|---|---|---|
| 6.8818 | 0.28 | 500 | 7.0258 | 1.0 |
| 6.7558 | 0.56 | 1000 | 6.9731 | 1.0 |
| 6.587 | 0.84 | 1500 | 6.9588 | 2.0097 |
| 6.881 | 1.12 | 2000 | 6.9579 | 2.0097 |
| 6.9616 | 1.4 | 2500 | 6.9553 | 2.0097 |
| 6.8572 | 1.68 | 3000 | 6.9488 | 2.0097 |
| 6.8827 | 1.96 | 3500 | 6.9496 | 2.0097 |
| 6.8313 | 2.24 | 4000 | 6.9496 | 2.0097 |
| 6.9634 | 2.52 | 4500 | 6.9445 | 2.0097 |
| 6.7935 | 2.8 | 5000 | 6.9553 | 2.0097 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu113
- Datasets 1.18.3
- Tokenizers 0.11.0