metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: emergency_09_tiny
results: []
emergency_09_tiny
This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0711
- Wer: 5.1329
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 32
- seed: 42
- 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: 500
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.01 | 15.625 | 500 | 0.0592 | 6.5995 |
| 0.0022 | 31.25 | 1000 | 0.0613 | 5.4079 |
| 0.0001 | 46.875 | 1500 | 0.0671 | 4.9496 |
| 0.0001 | 62.5 | 2000 | 0.0691 | 5.0412 |
| 0.0001 | 78.125 | 2500 | 0.0706 | 5.1329 |
| 0.0001 | 93.75 | 3000 | 0.0711 | 5.1329 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0