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-car50_e3n4_voiceless_mix_voiced_owner12_copy1x-241203-v1
results: []
whisper-large-v2-ft-car50_e3n4_voiceless_mix_voiced_owner12_copy1x-241203-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: 2.6578
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 |
|---|---|---|---|
| 11.5548 | 1.0 | 5 | 9.6624 |
| 7.4639 | 2.0 | 10 | 4.9015 |
| 4.3281 | 3.0 | 15 | 3.7228 |
| 3.6059 | 4.0 | 20 | 3.3802 |
| 3.3168 | 5.0 | 25 | 3.1692 |
| 3.1027 | 6.0 | 30 | 2.9916 |
| 2.9387 | 7.0 | 35 | 2.8507 |
| 2.807 | 8.0 | 40 | 2.7474 |
| 2.7155 | 9.0 | 45 | 2.6823 |
| 2.6691 | 10.0 | 50 | 2.6578 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.0