my_zh_CN_asr_cv13_model
This model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1614
- Cer: 0.0674
- Wer: 0.375
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 |
|---|---|---|---|---|---|
| 0.0489 | 249.002 | 1000 | 0.1566 | 0.0638 | 0.375 |
| 0.0224 | 499.002 | 2000 | 0.1614 | 0.0674 | 0.375 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1