wav2vec2-large-xls-r-300m-bn-colab

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_9_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4662
• Wer: 0.9861

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: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• 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: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
5.278	0.88	400	2.1963	1.0
0.8479	1.77	800	0.4662	0.9861

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1