kkkh_w2v2_large_finetune_teacher_babble_noise_mozilla_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: 24.1934
• Wer: 0.2500

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
791.6482	8.78	150	30.5908	0.2961
509.9743	17.55	300	26.0843	0.2612
457.1243	26.33	450	25.0523	0.2562
432.307	35.11	600	24.4050	0.2510
420.762	43.89	750	24.1934	0.2500

Framework versions

• Transformers 4.29.2
• Pytorch 1.12.1
• Datasets 2.6.1
• Tokenizers 0.13.1