metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: model
results: []
model
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.2495
- Wer: 128.4098
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.6384 | 3.13 | 1000 | 3.1848 | 127.8443 |
| 0.223 | 6.27 | 2000 | 3.7440 | 126.2142 |
| 0.0056 | 9.4 | 3000 | 4.1320 | 138.1238 |
| 0.001 | 12.54 | 4000 | 4.2495 | 128.4098 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.12.0+cu116
- Datasets 2.6.1
- Tokenizers 0.13.1