may-asr

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:

• Wer: 0.6811

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: 10

Training results

Training Loss	Epoch	Step	Wer
5.7712	3.2	400	0.9727
1.0877	6.4	800	0.7461
0.7746	9.6	1200	0.6811

Framework versions

• Transformers 4.33.1
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.13.3