wav2vec2vncskh

This model is a fine-tuned version of linl03/wav2vec2vncskh on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6088
• Wer: 0.9995

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: 32
• 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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.9335	8.06	500	1.3712	1.0
1.6652	16.13	1000	0.7927	0.9995
1.2043	24.19	1500	0.6088	0.9995

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0