mms-1b-finetuned-khm
This model is a fine-tuned version of facebook/mms-1b-fl102 on the seanghay/khmer-mpwt-speech dataset. It achieves the following results on the evaluation set:
- Loss: 0.5778
- Wer: 0.6278
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.8181 | 0.5587 | 100 | 1.0119 | 0.9584 |
| 1.1491 | 1.1173 | 200 | 0.7723 | 0.7366 |
| 0.9737 | 1.6760 | 300 | 0.6707 | 0.7366 |
| 0.8471 | 2.2346 | 400 | 0.6370 | 0.7019 |
| 0.8114 | 2.7933 | 500 | 0.5789 | 0.6863 |
| 0.6951 | 3.3520 | 600 | 0.5461 | 0.6464 |
| 0.6791 | 3.9106 | 700 | 0.5406 | 0.6672 |
Framework versions
- Transformers 4.57.0.dev0
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
- Downloads last month
- 3
Model tree for KrorngAI/mms-1b-fl102-finetuned-khm
Base model
facebook/mms-1b-fl102