output

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: 3.3931
• Wer: 1.0
• Cer: 0.9944

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: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.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: 5
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
7.136	0.3279	20	3.5020	1.0	0.9944
3.4969	0.6557	40	3.4605	1.0	0.9944
3.4509	0.9836	60	3.4172	1.0	0.9944
3.4449	1.3115	80	3.4042	1.0	0.9944
3.4074	1.6393	100	3.3931	1.0	0.9944
3.4072	1.9672	120	3.3931	1.0	0.9944

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0