wav2vec2-tk

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:

• Loss: 0.6088
• Wer: 0.6687

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: 0.0003
• train_batch_size: 1
• 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: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.0702	0.29	1000	1.4170	0.9376
1.1914	0.58	2000	1.0082	0.8331
0.8249	0.86	3000	0.6088	0.6687

Framework versions

• Transformers 4.26.1
• Pytorch 1.10.0+cu113
• Datasets 1.18.3
• Tokenizers 0.13.2