wav2vec2-teacher-student-en-asr-timit

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: 0.2592
• eval_wer: 0.3344
• eval_runtime: 79.9525
• eval_samples_per_second: 21.012
• eval_steps_per_second: 2.627
• epoch: 29.12
• step: 14500

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: 0.0001
• train_batch_size: 8
• 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: 32
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 1.18.3
• Tokenizers 0.13.2