wav2vec2-Pratyush-indian

This model is a fine-tuned version of Maverick1713/wav2vec2-Pratyush-indian on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.5013
• Wer: 0.3597

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 10
• total_train_batch_size: 20
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 15
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.364	0.5564	500	1.0113	0.5532
1.1626	1.1128	1000	0.8582	0.5019
0.9774	1.6693	1500	0.7245	0.4492
0.8462	2.2257	2000	0.6648	0.4191
0.7416	2.7821	2500	0.5721	0.3959
0.6595	3.3385	3000	0.5379	0.3723
0.5948	3.8949	3500	0.5013	0.3597

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1