wav2vec-large-xls-r-300-ha-colab_2

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_10_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4473
• Wer: 0.4392

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: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0168	5.19	400	0.4473	0.4392
0.0167	10.39	800	0.4473	0.4392
0.0166	15.58	1200	0.4473	0.4392
0.0172	20.77	1600	0.4473	0.4392
0.0166	25.97	2000	0.4473	0.4392

Framework versions

• Transformers 4.11.3
• Pytorch 1.10.0+cu113
• Datasets 2.3.2
• Tokenizers 0.10.3