wav2vec2-large-xls-r-300m-dm32

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5126
• Accuracy: 0.8000

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• 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: cosine_with_restarts
• lr_scheduler_warmup_steps: 100
• num_epochs: 22
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6359	4.1778	50	0.5819	0.8000
0.589	8.3556	100	0.5111	0.8000
0.5847	12.5333	150	0.5133	0.8000
0.5793	16.7111	200	0.5123	0.8000
0.5849	20.8889	250	0.5126	0.8000

Framework versions

• Transformers 4.53.2
• Pytorch 2.7.1+cu126
• Datasets 4.0.0
• Tokenizers 0.21.2