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__car50-realworld-e3n4-and-n4r2_owner12-copy2x-241209-v1
results: []
whisper-large-v2-ft-cv16-1__car50-realworld-e3n4-and-n4r2_owner12-copy2x-241209-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: 0.1143
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 |
|---|---|---|---|
| 4.3942 | 1.0 | 65 | 2.3210 |
| 1.4058 | 2.0 | 130 | 0.9391 |
| 0.1794 | 3.0 | 195 | 0.1194 |
| 0.126 | 4.0 | 260 | 0.1130 |
| 0.109 | 5.0 | 325 | 0.1117 |
| 0.0959 | 6.0 | 390 | 0.1120 |
| 0.0868 | 7.0 | 455 | 0.1118 |
| 0.0793 | 8.0 | 520 | 0.1129 |
| 0.0735 | 9.0 | 585 | 0.1138 |
| 0.0708 | 10.0 | 650 | 0.1143 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.0