metadata
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-kk-sp2n-b8-ms2000-s
results: []
whisper-kk-sp2n-b8-ms2000-s
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9067
- Wer: 152.0122
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.9003 | 0.11 | 1000 | 1.7087 | 152.9136 |
| 0.8546 | 0.23 | 2000 | 1.9067 | 152.0122 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3