metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-base-en
results: []
whisper-base-en
This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1362
- Wer: 4.3516
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-06
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- 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
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0146 | 0.4 | 100 | 0.1223 | 4.8708 |
| 0.0159 | 0.8 | 200 | 0.1248 | 4.8306 |
| 0.0104 | 1.2 | 300 | 0.1251 | 4.3803 |
| 0.01 | 1.6 | 400 | 0.1259 | 4.3975 |
| 0.0092 | 2.0 | 500 | 0.1263 | 4.4749 |
| 0.0055 | 2.4 | 600 | 0.1301 | 4.3344 |
| 0.0062 | 2.8 | 700 | 0.1303 | 4.4061 |
| 0.0039 | 3.2 | 800 | 0.1324 | 4.5294 |
| 0.0045 | 3.6 | 900 | 0.1337 | 4.3889 |
| 0.0036 | 4.0 | 1000 | 0.1350 | 4.2626 |
| 0.0033 | 4.4 | 1100 | 0.1358 | 4.3344 |
| 0.0033 | 4.8 | 1200 | 0.1362 | 4.3516 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3