hubert-base-timit-demo-colab

This model is a fine-tuned version of facebook/hubert-large-ls960-ft on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1092
• Wer: 0.1728

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: 32
• 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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
5.4664	4.0	500	2.3026	0.9866
0.8171	8.0	1000	0.0980	0.1885
0.2983	12.0	1500	0.0943	0.1750
0.1769	16.0	2000	0.0990	0.1737
0.1823	20.0	2500	0.1068	0.1757
0.0761	24.0	3000	0.1041	0.1719
0.0993	28.0	3500	0.1092	0.1728

Framework versions

• Transformers 4.13.0
• Pytorch 1.10.0+cu111
• Datasets 1.16.1
• Tokenizers 0.10.3