wav2vec2-large-TIMIT-IPA2

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

• Loss: 0.1531
• Per: 0.0638

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: 64
• eval_batch_size: 16
• 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: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Per
2.0846	6.85	500	0.1810	0.0991
0.1857	13.7	1000	0.1411	0.0691
0.0948	20.55	1500	0.1345	0.0666
0.0646	27.4	2000	0.1444	0.0673
0.0502	34.25	2500	0.1436	0.0628
0.0381	41.1	3000	0.1383	0.0637
0.0309	47.95	3500	0.1533	0.0638
0.0261	54.79	4000	0.1531	0.0638

Framework versions

• Transformers 4.20.0
• Pytorch 1.12.1+cu113
• Datasets 2.6.2.dev0
• Tokenizers 0.12.1