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: 0.1552
- Cer: 13.5275
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.1733 | 1.8622 | 500 | 0.1206 | 7.2293 |
| 0.1159 | 3.7244 | 1000 | 0.1404 | 10.6943 |
| 0.0596 | 5.5866 | 1500 | 0.1665 | 12.2340 |
| 0.0399 | 7.4488 | 2000 | 0.1486 | 11.8316 |
| 0.0224 | 9.3110 | 2500 | 0.1552 | 13.5275 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1