metadata
library_name: transformers
license: mit
base_model: Vira21/Whisper-Base-KhmerV2
tags:
- generated_from_trainer
datasets:
- fleurs
metrics:
- wer
model-index:
- name: whisper-base-khmer-v2
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: fleurs
type: fleurs
config: km_kh
split: test
args: km_kh
metrics:
- name: Wer
type: wer
value: 0.609560191987462
whisper-base-khmer-v2
This model is a fine-tuned version of Vira21/Whisper-Base-KhmerV2 on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.2003
- Wer: 0.6096
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Use adamw_torch 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 |
|---|---|---|---|---|
| 0.1065 | 0.3171 | 50 | 0.2027 | 0.6121 |
| 0.0973 | 0.6342 | 100 | 0.2014 | 0.6138 |
| 0.0933 | 0.9512 | 150 | 0.2003 | 0.6096 |
| 0.0816 | 1.2727 | 200 | 0.2020 | 0.6125 |
| 0.0767 | 1.5898 | 250 | 0.2025 | 0.6131 |
| 0.0782 | 1.9069 | 300 | 0.2027 | 0.6096 |
| 0.0728 | 2.2283 | 350 | 0.2044 | 0.6097 |
| 0.0692 | 2.5454 | 400 | 0.2043 | 0.6131 |
| 0.0685 | 2.8625 | 450 | 0.2043 | 0.6125 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.3.1
- Tokenizers 0.21.0