wav2vec2-base-timit-demo-colab-2

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

• Loss: 0.7429
• Wer: 0.5080

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: 0.0005
• train_batch_size: 10
• 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: 900
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.984	8.77	500	0.9028	0.7036
0.6412	17.54	1000	0.7275	0.5868
0.3073	26.32	1500	0.7429	0.5080

Framework versions

• Transformers 4.11.3
• Pytorch 1.11.0+cu113
• Datasets 1.18.3
• Tokenizers 0.10.3