wav2vec2-large-xls-wolof-asr

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: 0.2295
• Wer: 0.2106

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.947	9.3	400	0.4350	0.4696
0.234	18.6	800	0.2276	0.2405
0.0788	27.91	1200	0.2295	0.2106

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 1.18.3
• Tokenizers 0.13.3