krishivoice

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: 0.6148
• Wer: 0.2809

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: 8
• 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: 200
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3768	9.0909	1000	0.5920	0.4378
0.1392	18.1818	2000	0.5513	0.3537
0.0823	27.2727	3000	0.5021	0.3260
0.0566	36.3636	4000	0.5473	0.3163
0.0886	45.4545	5000	0.5637	0.3098
0.0368	54.5455	6000	0.5558	0.3004
0.0264	63.6364	7000	0.6315	0.2919
0.0214	72.7273	8000	0.5927	0.2902
0.0124	81.8182	9000	0.6936	0.2874
0.0132	90.9091	10000	0.6311	0.2858
0.0094	100.0	11000	0.6148	0.2809

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1