metadata
library_name: transformers
language:
- th
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- fsicoli/common_voice_22_0
metrics:
- wer
model-index:
- name: Whisper Small Th - Testhai
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 22.0
type: fsicoli/common_voice_22_0
config: th
split: test[:2%]
args: 'config: th, split: test'
metrics:
- name: Wer
type: wer
value: 100
Whisper Small Th - Testhai
This model is a fine-tuned version of openai/whisper-small on the Common Voice 22.0 dataset. It achieves the following results on the evaluation set:
- Loss: 2.9453
- Wer: 100.0
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: 0.001
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.3587 | 1.0 | 330 | 3.2810 | 100.0 |
| 2.2188 | 2.0 | 660 | 3.0993 | 100.0 |
| 2.4391 | 3.0 | 990 | 2.9453 | 100.0 |
Framework versions
- Transformers 5.9.0
- Pytorch 2.12.0+cu132
- Datasets 4.8.5
- Tokenizers 0.22.2