wav2vec2-nepali-asr

This model is a fine-tuned version of Strange18/wav2vec2-nepali-asr on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3957
• Wer: 0.3705

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.7578	1.5464	75	0.5105	0.4879
0.6844	3.0928	150	0.4736	0.4575
0.6367	4.6392	225	0.4586	0.4291
0.5977	6.1856	300	0.4387	0.4170
0.5714	7.7320	375	0.4350	0.4170
0.5815	9.2784	450	0.4255	0.4109
0.5629	10.8247	525	0.4260	0.4049

Framework versions

• Transformers 4.42.3
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.19.1