wav2vec2-model-training

This model is a fine-tuned version of facebook/wav2vec2-base on the lj_speech dataset. It achieves the following results on the evaluation set:

• Loss: 0.1258
• Wer: 0.1446

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.5099	1.52	500	1.1323	0.6740
0.3293	3.05	1000	0.1430	0.1851
0.1047	4.57	1500	0.1258	0.1446

Framework versions

• Transformers 4.17.0
• Pytorch 2.1.2
• Datasets 2.15.0
• Tokenizers 0.15.2