Edit model card

wav2vec2-xls-r-300m-gl-CV8

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2151
  • Wer: 0.2080

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: 0.0001
  • 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: 300
  • num_epochs: 15
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
4.9427 4.9 500 2.8801 1.0
2.1594 9.8 1000 0.4092 0.4001
0.7332 14.71 1500 0.2151 0.2080

Framework versions

  • Transformers 4.11.3
  • Pytorch 1.10.0+cu111
  • Datasets 1.18.1
  • Tokenizers 0.10.3
Downloads last month
13

Dataset used to train emre/wav2vec2-xls-r-300m-gl-CV8

Evaluation results