mr_sam_wav2vec2_nigerian_accent_v2

This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.5990
• Wer: 0.9805

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
14.8323	0.3958	300	4.8319	0.9805
5.0328	0.7916	600	3.5990	0.9805

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1