Edit model card

Model_G_Wav2Vec2_Versi1

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: 0.4072
  • Wer: 1.0101
  • Cer: 0.7622

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 Cer
3.7506 5.97 400 0.6970 1.0124 0.7636
0.3678 11.94 800 0.4711 1.0290 0.7660
0.1612 17.91 1200 0.4492 1.0007 0.7606
0.1056 23.88 1600 0.4012 1.0040 0.7658
0.0693 29.85 2000 0.4072 1.0101 0.7622

Framework versions

  • Transformers 4.11.3
  • Pytorch 1.10.0+cu113
  • Datasets 1.18.3
  • Tokenizers 0.10.3
Downloads last month
0

Dataset used to train rossevine/Model_G_Wav2Vec2_Versi1