metadata
library_name: transformers
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-large-v2_lv_60
results: []
whisper-large-v2_lv_60
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8488
- Wer: 40.1058
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: 3e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.7165 | 1.2594 | 1000 | 0.5753 | 48.6640 |
| 4.5588 | 2.5189 | 2000 | 0.5946 | 39.7174 |
| 3.1389 | 3.7783 | 3000 | 0.6317 | 41.1180 |
| 1.1761 | 5.0378 | 4000 | 0.7433 | 39.6426 |
| 1.0312 | 6.2972 | 5000 | 0.7913 | 39.5923 |
| 0.9134 | 7.5567 | 6000 | 0.8488 | 40.1058 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0