tuanio/1-epochs1.0-char-based-freeze_cnn-dropout0.1

<!-- 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. -->

1-epochs1.0-char-based-freeze_cnn-dropout0.1

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

• —Loss: 0.6141
• —Wer: 0.4516

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: 2e-05
• —trainbatchsize: 10
• —evalbatchsize: 4
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 4
• —totaltrainbatch_size: 40
• —totalevalbatch_size: 16
• —optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 1.0

Training results

Framework versions

• —Transformers 4.34.0
• —Pytorch 2.0.1
• —Datasets 2.14.5
• —Tokenizers 0.14.1