training

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: 2.0763
• Wer: 0.9551

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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: 25
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.6154	3.3557	500	3.6223	1.0
3.6729	6.7114	1000	3.5869	1.0
3.6718	10.0671	1500	3.5824	1.0
3.7365	13.4228	2000	3.5829	1.0
3.5897	16.7785	2500	3.5750	1.0
3.5689	20.1342	3000	3.2325	1.0
2.4663	23.4899	3500	2.0763	0.9551

Framework versions

• Transformers 4.57.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.22.1