my_jp_asr_cv13_model
This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-japanese on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 3.1772
- Cer: 0.3512
- Wer: 0.875
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: 2
- total_train_batch_size: 16
- 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 | Cer | Wer |
|---|---|---|---|---|---|
| 0.16 | 250.0 | 1000 | 3.1440 | 0.3223 | 0.875 |
| 0.1061 | 500.0 | 2000 | 3.1772 | 0.3512 | 0.875 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1