wav2vec2-large-xlsr-53-ha-colab_1

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice_10_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.7843
• Wer: 0.4827

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
5.2849	5.19	400	2.8140	1.0
1.4323	10.39	800	0.6695	0.5772
0.2833	15.58	1200	0.6866	0.5036
0.1798	20.77	1600	0.7698	0.4950
0.1369	25.97	2000	0.7843	0.4827

Framework versions

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