C0_LID_DEV

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: inf
• Wer: 0.8267

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: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0.0	25	inf	0.8426
1.5354	0.17	2000	inf	0.8198
1.5688	0.33	4000	inf	0.8271
1.5294	0.5	6000	inf	0.8339
1.1947	0.67	8000	inf	0.8260
1.1534	0.83	10000	inf	0.8267
1.1484	1.0	12000	inf	0.8267

Framework versions

• Transformers 4.11.3
• Pytorch 1.10.2+cu113
• Datasets 1.18.3
• Tokenizers 0.10.3