xlsr-nm-nor

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3194
• Wer: 0.3191

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: 0.0004
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 132
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.7474	11.1143	200	2.9646	1.0
2.5674	22.2286	400	1.7315	1.0
0.8551	33.3429	600	0.4517	0.4125
0.2155	44.4571	800	0.3589	0.3424
0.1316	55.5714	1000	0.2728	0.3191
0.0667	66.6857	1200	0.3201	0.3735
0.0466	77.8	1400	0.3268	0.3230
0.0316	88.9143	1600	0.3194	0.3191

Framework versions

• Transformers 4.47.0.dev0
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0