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-my_dataset_car100_owner12_snr0x8_mp3-241019-v1
results: []
whisper-large-v2-ft-my_dataset_car100_owner12_snr0x8_mp3-241019-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: 4.8495
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 |
|---|---|---|---|
| 11.2648 | 1.0 | 1 | 11.5108 |
| 11.3659 | 2.0 | 2 | 10.3712 |
| 10.3532 | 3.0 | 3 | 8.2361 |
| 8.0834 | 4.0 | 4 | 7.1707 |
| 6.6524 | 5.0 | 5 | 6.3952 |
| 6.0037 | 6.0 | 6 | 5.7626 |
| 5.5881 | 7.0 | 7 | 5.3653 |
| 5.4891 | 8.0 | 8 | 5.0994 |
| 5.2076 | 9.0 | 9 | 4.9297 |
| 4.9913 | 10.0 | 10 | 4.8495 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.0