asr_mind_mode
This model is a fine-tuned version of w11wo/wav2vec2-xls-r-300m-korean on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7080
- Wer: 0.7078
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- 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: 5
- training_steps: 60
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.9489 | 0.1688 | 20 | 2.2363 | 0.7466 |
| 5.0448 | 0.3376 | 40 | 1.8017 | 0.7313 |
| 4.5643 | 0.5063 | 60 | 1.7080 | 0.7078 |
Framework versions
- Transformers 5.20.2
- Pytorch 2.14.1+cu130
- Datasets 4.8.5
- Tokenizers 0.23.3
- Downloads last month
- -
Model tree for Uj-02/asr_mind_mode
Base model
w11wo/wav2vec2-xls-r-300m-korean