vast_base_last

This model is a fine-tuned version of facebook/wav2vec2-base on the timit_asr dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.3753
• eval_cer: 0.1234
• eval_runtime: 16.2989
• eval_samples_per_second: 51.537
• eval_steps_per_second: 6.442
• epoch: 11.24
• step: 2800

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: 16
• 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: 25
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.17.0
• Pytorch 2.4.0
• Datasets 1.18.3
• Tokenizers 0.20.3