metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-base-akan
results: []
whisper-base-akan
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: 1.0030
- Wer: 41.5869
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2883 | 5.0 | 250 | 0.7379 | 70.2488 |
| 0.0873 | 10.0 | 500 | 0.8617 | 49.6246 |
| 0.0373 | 15.0 | 750 | 0.9027 | 47.4165 |
| 0.0204 | 20.0 | 1000 | 0.9374 | 44.5017 |
| 0.0078 | 25.0 | 1250 | 0.9861 | 44.0601 |
| 0.0014 | 30.0 | 1500 | 0.9873 | 42.1758 |
| 0.0003 | 35.0 | 1750 | 0.9982 | 41.4544 |
| 0.0003 | 40.0 | 2000 | 1.0030 | 41.5869 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1