w2v-xlsr-2.0-train_3

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: 0.6887
• Wer: 0.4170

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 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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.7778	4.5455	500	0.7334	0.6573
0.2331	9.0909	1000	0.5910	0.4974
0.1413	13.6364	1500	0.6484	0.4803
0.106	18.1818	2000	0.6719	0.4568
0.0883	22.7273	2500	0.6793	0.4336
0.0636	27.2727	3000	0.6887	0.4170

Framework versions

• Transformers 4.48.3
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.21.0