<!-- 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. -->
faiq-wav2vec2-large-xlsr-indo-demo-a100-40-batch32
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3581
- Wer: 0.4248
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: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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 |
---|---|---|---|---|
4.5172 | 5.84 | 400 | 2.7350 | 1.0012 |
0.8858 | 11.68 | 800 | 0.3838 | 0.5132 |
0.2526 | 17.52 | 1200 | 0.3482 | 0.4563 |
0.1719 | 23.36 | 1600 | 0.3652 | 0.4374 |
0.1403 | 29.2 | 2000 | 0.3581 | 0.4248 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu117
- Datasets 2.6.1
- Tokenizers 0.13.3