RuiqianLi/wav2vec2-large-960h-lv60-self-4-gram_fine-tune_real_29_Jun

<!-- 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-large-960h-lv60-self-4-gramfine-tunereal29Jun

This model is a fine-tuned version of facebook/wav2vec2-large-960h-lv60-self on the uob_singlish dataset. It achieves the following results on the evaluation set:

• —Loss: 1.2895
• —Wer: 0.4583

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: 0.0002
• —trainbatchsize: 2
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 4
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 10
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.11.3
• —Pytorch 1.10.0+cu113
• —Datasets 1.18.3
• —Tokenizers 0.10.3