wev2vec-base960-agu-amharic

This model is a fine-tuned version of facebook/wav2vec2-base-960h on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3117
• Accuracy: 0.9230

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: 1e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8682	0.6649	500	0.7632	0.7564
0.4482	1.3298	1000	0.3501	0.9103
0.2724	1.9947	1500	0.3117	0.9230
0.2269	2.6596	2000	0.3456	0.9268
0.1663	3.3245	2500	0.3743	0.9275
0.1737	3.9894	3000	0.3714	0.9327

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1