metadata
library_name: transformers
license: apache-2.0
base_model: biodatlab/whisper-th-small-combined
tags:
- generated_from_trainer
model-index:
- name: outs
results: []
outs
This model is a fine-tuned version of biodatlab/whisper-th-small-combined on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1631
- Cer: 10.9836
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2.0
- total_train_batch_size: 32.0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| No log | 0.9926 | 67 | 0.1876 | 10.2687 |
| 0.1249 | 2.0 | 135 | 0.1632 | 13.0653 |
| 0.0715 | 2.9926 | 202 | 0.1870 | 14.0862 |
| 0.0715 | 4.0 | 270 | 0.1636 | 10.3119 |
| 0.0386 | 4.9630 | 335 | 0.1631 | 10.9836 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1