metadata
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-med-LoRA_nosie_128_256_45k
results: []
whisper-med-LoRA_nosie_128_256_45k
This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1914
- Wer: 8.6601
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5111 | 1.0 | 2863 | 0.2845 | 11.9909 |
| 0.2265 | 2.0 | 5726 | 0.2335 | 10.3921 |
| 0.1772 | 3.0 | 8589 | 0.2106 | 9.4024 |
| 0.1495 | 4.0 | 11452 | 0.1959 | 9.0027 |
| 0.1331 | 5.0 | 14315 | 0.1914 | 8.6601 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3