metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
base_model: openai/whisper-medium
model-index:
- name: whisper-medium-ckb
results: []
whisper-medium-ckb
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: 0.2977
- Wer: 31.3503
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1833
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.27 | 1.03 | 366 | 0.2722 | 43.9177 |
| 0.1498 | 2.07 | 732 | 0.2354 | 36.2845 |
| 0.0538 | 3.1 | 1098 | 0.2422 | 33.6539 |
| 0.0168 | 4.14 | 1464 | 0.2717 | 32.3842 |
| 0.0025 | 6.0 | 1830 | 0.2977 | 31.3503 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2