hubert-large-timit-ft

This model is a fine-tuned version of facebook/hubert-large-ls960-ft on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 24.5101
• Wer: 0.6804

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: 0.0003
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
68.4493	0.6192	500	52.8444	0.9256
41.8552	1.2378	1000	38.5239	0.9110
35.106	1.8570	1500	30.3103	0.7391
32.154	2.4755	2000	24.5101	0.6804

Framework versions

• Transformers 4.51.3
• Pytorch 2.2.1
• Datasets 3.6.0
• Tokenizers 0.21.1