metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
model-index:
- name: whisper-small-me
results: []
whisper-small-me
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4509
- Mazanderani Wer: 0.5278
- Mazanderani Cer: 0.1615
- Gilaki Wer: 0.9176
- Gilaki Cer: 0.3175
- Zazaki Wer: 0.6324
- Zazaki Cer: 0.2020
- Laki Kurdish Wer: 0.4904
- Laki Kurdish Cer: 0.1247
- Talysh Wer: 1.0
- Talysh Cer: 0.5
- Hawrami Wer: 0.3459
- Hawrami Cer: 0.0708
- Southern Kurdish Wer: 0.4930
- Southern Kurdish Cer: 0.1718
- Avg Wer: 0.6296
- Avg Cer: 0.2212
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: 128
- eval_batch_size: 128
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 256
- total_eval_batch_size: 256
- 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: 100
- num_epochs: 5.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Mazanderani Wer | Mazanderani Cer | Gilaki Wer | Gilaki Cer | Zazaki Wer | Zazaki Cer | Laki Kurdish Wer | Laki Kurdish Cer | Talysh Wer | Talysh Cer | Hawrami Wer | Hawrami Cer | Southern Kurdish Wer | Southern Kurdish Cer | Avg Wer | Avg Cer |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.6946 | 1.0 | 82 | 0.7662 | 0.8120 | 0.3224 | 0.9556 | 0.3751 | 1.0270 | 1.0389 | 0.7939 | 0.2733 | 0.9167 | 0.3333 | 0.5246 | 0.1155 | 0.6801 | 0.2192 | 0.8157 | 0.3825 |
| 0.3864 | 2.0 | 164 | 0.5172 | 0.6093 | 0.1846 | 0.9579 | 0.3454 | 0.7451 | 0.2813 | 0.5644 | 0.1547 | 1.0 | 0.5 | 0.3806 | 0.0773 | 0.5484 | 0.1743 | 0.6865 | 0.2454 |
| 0.3234 | 3.0 | 246 | 0.4686 | 0.5476 | 0.1652 | 0.9633 | 0.3514 | 0.6740 | 0.2363 | 0.5231 | 0.1362 | 1.0 | 0.5 | 0.3533 | 0.0722 | 0.4936 | 0.1674 | 0.6507 | 0.2327 |
| 0.2786 | 4.0 | 328 | 0.4527 | 0.5278 | 0.1596 | 0.9083 | 0.3179 | 0.6422 | 0.2133 | 0.5047 | 0.1334 | 1.0 | 0.5 | 0.3485 | 0.0732 | 0.4948 | 0.1769 | 0.6323 | 0.2249 |
| 0.2586 | 5.0 | 410 | 0.4509 | 0.5278 | 0.1615 | 0.9176 | 0.3175 | 0.6324 | 0.2020 | 0.4904 | 0.1247 | 1.0 | 0.5 | 0.3459 | 0.0708 | 0.4930 | 0.1718 | 0.6296 | 0.2212 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0