<!-- 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-base-dementiabank

This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 11.0473
• eval_wer: 1.0
• eval_runtime: 3.3353
• eval_samples_per_second: 2.399
• eval_steps_per_second: 0.3
• epoch: 3.12
• step: 200

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: 0.5
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 5
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.11.3
• Pytorch 1.10.0+cu111
• Datasets 1.13.3
• Tokenizers 0.10.3