xls-r-300m-cicipu-120

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: 0.0114
• Cer: 0.0025

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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
5.5501	3.7070	400	3.4424	0.9979
2.1441	7.4093	800	0.9462	0.2134
1.1888	11.1116	1200	0.4379	0.1052
0.7868	14.8186	1600	0.2077	0.0514
0.5468	18.5209	2000	0.0956	0.0269
0.3864	22.2233	2400	0.0412	0.0089
0.2966	25.9302	2800	0.0189	0.0046
0.2269	29.6326	3200	0.0114	0.0025

Framework versions

• Transformers 4.49.0.dev0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0