metadata
library_name: transformers
language:
- th
license: apache-2.0
base_model: openai/whisper-medium
tags:
- asr
- speech-recognition
- thai
- custom-model
- fine-tuning
- Common Voice
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Medium TH - Custom datasets
results: []
Whisper Medium TH - Custom datasets
This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2140
- Wer: 64.6555
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: 16
- 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: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1857 | 1.2019 | 500 | 0.2235 | 77.0195 |
| 0.0619 | 2.4038 | 1000 | 0.2041 | 71.8431 |
| 0.019 | 3.6058 | 1500 | 0.2073 | 67.9855 |
| 0.0067 | 4.8077 | 2000 | 0.2140 | 64.6555 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3