metadata
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
model-index:
- name: MAScIR_elderly_whisper-medium-LoRA-ev
results: []
MAScIR_elderly_whisper-medium-LoRA-ev
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: 0.0213
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 |
|---|---|---|---|
| 0.3194 | 0.19 | 100 | 0.2974 |
| 0.2485 | 0.37 | 200 | 0.2865 |
| 0.2532 | 0.56 | 300 | 0.2810 |
| 0.2306 | 0.74 | 400 | 0.2225 |
| 0.1954 | 0.93 | 500 | 0.2355 |
| 0.1178 | 1.11 | 600 | 0.1883 |
| 0.1087 | 1.3 | 700 | 0.1567 |
| 0.098 | 1.48 | 800 | 0.1593 |
| 0.0661 | 1.67 | 900 | 0.0985 |
| 0.0675 | 1.85 | 1000 | 0.0602 |
| 0.0297 | 2.04 | 1100 | 0.0543 |
| 0.0172 | 2.22 | 1200 | 0.0436 |
| 0.0157 | 2.41 | 1300 | 0.0403 |
| 0.0143 | 2.59 | 1400 | 0.0317 |
| 0.0167 | 2.78 | 1500 | 0.0265 |
| 0.0095 | 2.96 | 1600 | 0.0213 |
Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3