wav2vec2-common-voice-17_0_vi

This model is a fine-tuned version of nguyenvulebinh/wav2vec2-base-vietnamese-250h on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.7992
• Wer: 0.4349

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: 0.0001
• train_batch_size: 8
• 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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.261	4.3103	500	0.4182	0.3492
0.2061	8.6207	1000	0.5416	0.4044
0.1883	12.9310	1500	0.6796	0.4304
0.1336	17.2414	2000	0.8089	0.4378
0.1257	21.5517	2500	0.8244	0.4426
0.098	25.8621	3000	0.7992	0.4349

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1