metadata
base_model: openai/whisper-large-v2
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: >-
whisper-large-v2-ft-cv16-1__my_dataset_car50_owner12_notmix_copy1x_mp3-241117-v1
results: []
whisper-large-v2-ft-cv16-1__my_dataset_car50_owner12_notmix_copy1x_mp3-241117-v1
This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1216
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: 5e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.3306 | 1.0 | 58 | 2.3090 |
| 1.5738 | 2.0 | 116 | 0.4297 |
| 0.1892 | 3.0 | 174 | 0.1239 |
| 0.136 | 4.0 | 232 | 0.1188 |
| 0.1174 | 5.0 | 290 | 0.1169 |
| 0.1049 | 6.0 | 348 | 0.1174 |
| 0.0949 | 7.0 | 406 | 0.1188 |
| 0.0884 | 8.0 | 464 | 0.1204 |
| 0.0824 | 9.0 | 522 | 0.1211 |
| 0.0795 | 10.0 | 580 | 0.1216 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.0