metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-large-v3-chichewa
results: []
whisper-large-v3-chichewa
This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9810
- Wer: 101.7738
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: 32
- eval_batch_size: 16
- 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: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.9765 | 5.2910 | 1000 | 1.8781 | 198.6546 |
| 0.2576 | 10.5820 | 2000 | 2.2548 | 81.4057 |
| 0.1191 | 15.8730 | 3000 | 2.4730 | 80.9351 |
| 0.0755 | 21.1640 | 4000 | 2.6557 | 79.4872 |
| 0.0726 | 26.4550 | 5000 | 2.6869 | 78.3228 |
| 0.0722 | 31.7460 | 6000 | 2.7548 | 93.2428 |
| 0.0624 | 37.0370 | 7000 | 2.8531 | 79.5958 |
| 0.0605 | 42.3280 | 8000 | 2.8869 | 77.6893 |
| 0.062 | 47.6190 | 9000 | 2.9388 | 86.6606 |
| 0.0515 | 52.9101 | 10000 | 2.9810 | 101.7738 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.0.1
- Datasets 3.0.1
- Tokenizers 0.20.0