wav2vec2-xls-r-300m-fula

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the ABDOUAZIIZ/FULA_WITHOUT_NUM - NA dataset. It achieves the following results on the evaluation set:

• Loss: 0.4631
• Wer: 1.0057

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: 12
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 24
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2000
• num_epochs: 30.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4752	1.0309	2000	0.5954	1.0
0.3858	2.0619	4000	0.4631	1.0057
0.3571	3.0928	6000	0.4864	1.0073
0.2857	4.1237	8000	0.4647	1.0008
0.2628	5.1546	10000	0.5844	1.0065

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1
• Datasets 2.20.0
• Tokenizers 0.19.1