metadata
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
model-index:
- name: MAScIR_elderly_whisper-medium-LoRA-for_test
results: []
MAScIR_elderly_whisper-medium-LoRA-for_test
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: 0.0403
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: 0.001
- 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: 200
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2935 | 0.19 | 100 | 0.2595 |
| 0.3101 | 0.38 | 200 | 0.2421 |
| 0.2404 | 0.57 | 300 | 0.2664 |
| 0.2303 | 0.76 | 400 | 0.2072 |
| 0.2021 | 0.95 | 500 | 0.1893 |
| 0.1075 | 1.14 | 600 | 0.1650 |
| 0.1222 | 1.33 | 700 | 0.1328 |
| 0.1036 | 1.52 | 800 | 0.1077 |
| 0.0908 | 1.71 | 900 | 0.0835 |
| 0.0701 | 1.9 | 1000 | 0.0727 |
| 0.029 | 2.09 | 1100 | 0.0587 |
| 0.0264 | 2.28 | 1200 | 0.0522 |
| 0.0164 | 2.47 | 1300 | 0.0507 |
| 0.0162 | 2.66 | 1400 | 0.0459 |
| 0.0151 | 2.85 | 1500 | 0.0403 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0