xls-r-300m-nyanja-model_v1

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

• Loss: 0.2772
• Wer: 0.9074

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: 0.001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2000
• num_epochs: 5.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.7585	1.58	500	0.3574	0.9679
0.4736	3.16	1000	0.2772	0.9074
0.4776	4.75	1500	0.2853	0.9578

Framework versions

• Transformers 4.25.0.dev0
• Pytorch 1.12.1+cu113
• Datasets 2.7.1
• Tokenizers 0.13.2