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: 1.1058
- Wer: 41.1088
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: 32
- 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 |
|---|---|---|---|---|
| 1.8723 | 10.0 | 250 | 1.0427 | 68.4371 |
| 0.3084 | 20.0 | 500 | 0.7759 | 44.8196 |
| 0.0708 | 30.0 | 750 | 0.9140 | 42.7532 |
| 0.027 | 40.0 | 1000 | 1.0043 | 42.5058 |
| 0.0109 | 50.0 | 1250 | 1.0740 | 42.1711 |
| 0.0046 | 60.0 | 1500 | 1.0846 | 40.9488 |
| 0.0032 | 70.0 | 1750 | 1.1017 | 41.3708 |
| 0.0022 | 80.0 | 2000 | 1.1058 | 41.1088 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0