rohitp1/libri-smallw2v2-no-copy-mse-alpha-0.75-T-1-take-2

<!-- 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. -->

libri-smallw2v2-no-copy-mse-alpha-0.75-T-1-take-2

This model is a fine-tuned version of rohitp1/libri-smallw2v2-no-copy-mse-alpha-0.75-T-1 on the None dataset. It achieves the following results on the evaluation set:

• —eval_loss: 221.7213
• —eval_wer: 0.4782
• —eval_runtime: 298.2644
• —evalsamplesper_second: 9.062
• —evalstepsper_second: 0.285
• —epoch: 66.0
• —step: 23562

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: 5e-05
• —trainbatchsize: 32
• —evalbatchsize: 32
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 64
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_ratio: 0.3
• —num_epochs: 100
• —mixedprecisiontraining: Native AMP

Framework versions

• —Transformers 4.25.1
• —Pytorch 1.12.1
• —Datasets 2.8.0
• —Tokenizers 0.13.2