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: 9.1883
- Wer: 2.0039
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 |
|---|---|---|---|---|
| 6.7101 | 0.28 | 500 | 6.8996 | 1.2137 |
| 6.5466 | 0.56 | 1000 | 6.7531 | 1.4516 |
| 6.1449 | 0.84 | 1500 | 6.6346 | 1.8296 |
| 6.5299 | 1.12 | 2000 | 6.5735 | 1.9686 |
| 6.6303 | 1.4 | 2500 | 6.6005 | 1.9392 |
| 6.4568 | 1.68 | 3000 | 6.6191 | 1.9739 |
| 6.4666 | 1.96 | 3500 | 7.4679 | 2.0081 |
| 6.2546 | 2.24 | 4000 | 7.7967 | 1.9948 |
| 6.4101 | 2.52 | 4500 | 8.1178 | 1.9956 |
| 6.142 | 2.8 | 5000 | 9.1883 | 2.0039 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu113
- Datasets 1.18.3
- Tokenizers 0.11.0