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 and Common voice 17
results: []
Whisper Medium TH - Custom datasets and Common voice 17
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: 0.1365
- Wer: 59.1432
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: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.267 | 0.2405 | 500 | 0.2401 | 77.2512 |
| 0.1975 | 0.4810 | 1000 | 0.1865 | 68.8672 |
| 0.1935 | 0.7215 | 1500 | 0.1659 | 64.4477 |
| 0.1591 | 0.9620 | 2000 | 0.1477 | 63.3167 |
| 0.0821 | 1.2025 | 2500 | 0.1431 | 60.2557 |
| 0.0762 | 1.4430 | 3000 | 0.1365 | 59.1432 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3