Whisper Small thai - neww tokenizer
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0-th-6500 sample dataset. It achieves the following results on the evaluation set:
- Loss: 0.2690
- Wer: 36.8393
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: 16
- eval_batch_size: 8
- 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: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1287 | 2.4570 | 1000 | 0.2690 | 36.8393 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for Chonlasitk/fine-tuned-wer-test2-whisper-small-th
Base model
openai/whisper-smallDataset used to train Chonlasitk/fine-tuned-wer-test2-whisper-small-th
Evaluation results
- Wer on Common Voice 11.0-th-6500 sampleself-reported36.839