wav2vec2-vocals

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1234
• Cer: 0.2848

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 12
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
6.9359	3.6496	500	2.8329	0.9873
1.1168	7.2993	1000	1.0561	0.3050
0.3139	10.9489	1500	1.1234	0.2848

Framework versions

• Transformers 4.40.1
• Pytorch 2.0.1+cu117
• Datasets 2.19.0
• Tokenizers 0.19.1