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_copy8x_mp3-241114-v1
results: []
whisper-large-v2-ft-cv16-1__my_dataset_car50_owner12_notmix_copy8x_mp3-241114-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: 0.1018
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 |
|---|---|---|---|
| 4.3903 | 1.0 | 75 | 2.2025 |
| 1.1765 | 2.0 | 150 | 0.1276 |
| 0.1351 | 3.0 | 225 | 0.1008 |
| 0.1071 | 4.0 | 300 | 0.0972 |
| 0.0925 | 5.0 | 375 | 0.0966 |
| 0.0813 | 6.0 | 450 | 0.0974 |
| 0.0722 | 7.0 | 525 | 0.0997 |
| 0.066 | 8.0 | 600 | 0.0998 |
| 0.0608 | 9.0 | 675 | 0.1019 |
| 0.0583 | 10.0 | 750 | 0.1018 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.0