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

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

• Loss: 1.6916
• Wer: 0.6686

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
7.495	4.6	400	3.4581	1.0
1.2055	9.2	800	1.6062	0.7986
0.3038	13.79	1200	1.5743	0.7307
0.1831	18.39	1600	1.6441	0.7119
0.1146	22.99	2000	1.6888	0.6977
0.0876	27.59	2400	1.6916	0.6686

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2