amar_model

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: 8.6180
• Wer: 1.0

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: 500
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
35.5043	1.6667	5	17.9174	1.0
34.6734	3.3333	10	17.7898	1.0
35.1143	5.0	15	17.5139	1.0
34.9785	6.6667	20	16.9785	1.0
32.6794	8.3333	25	16.0331	1.0
30.3481	10.0	30	14.2935	1.0
26.0362	11.6667	35	11.9324	1.0
22.2761	13.3333	40	9.9843	1.0
17.6623	15.0	45	8.6180	1.0

Framework versions

• Transformers 4.46.1
• Pytorch 2.4.1+cpu
• Datasets 3.1.0
• Tokenizers 0.20.1