metadata
library_name: peft
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
- generated_from_trainer
model-index:
- name: whisereer-v2
results: []
whisereer-v2
This model is a fine-tuned version of openai/whisper-large-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7024
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: 0.001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4577 | 1.0 | 853 | 1.7271 |
| 1.2127 | 2.0 | 1706 | 1.6592 |
| 1.024 | 3.0 | 2559 | 1.6661 |
| 0.7389 | 3.9959 | 3408 | 1.7024 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.5.1+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1