rohitp1/subh_w2v2_large_finetune_teacher_clean_mozilla_hours_50_epochs_batch_16

dgx1_w2v2_large_finetune_teacher_clean_mozilla_hours_50_epochs_batch_16

This model is a fine-tuned version of facebook/wav2vec2-large-960h-lv60 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 12.6398
• Wer: 0.1594

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 256
• total_train_batch_size: 4096
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.2
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
504.8802	8.78	150	14.7437	0.1802
308.4299	17.55	300	13.2490	0.1633
278.101	26.33	450	12.9519	0.1635
264.4989	35.11	600	12.7146	0.1609
257.3318	43.89	750	12.6398	0.1594

Framework versions

• Transformers 4.29.2
• Pytorch 1.12.1
• Datasets 2.8.0
• Tokenizers 0.13.2