<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
wav2vec2-tiengviet_vin
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4034
- Wer: 0.5523
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
5.4971 | 7.08 | 400 | 3.4550 | 0.9967 |
2.4704 | 14.16 | 800 | 1.3832 | 0.7137 |
1.0071 | 21.24 | 1200 | 1.3447 | 0.5908 |
0.6728 | 28.32 | 1600 | 1.4034 | 0.5523 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2