my_awesome_asr_mind_model

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

• Loss: 3.4146
• Wer: 1.0

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 30
• training_steps: 300
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
50.2402	6.0	30	35.6862	1.0
30.6841	12.0	60	6.6236	1.0
8.3238	18.0	90	4.0080	1.0
4.663	24.0	120	3.7875	1.0
3.986	30.0	150	3.6613	1.0
3.9205	36.0	180	3.5573	1.0
3.7835	42.0	210	3.4962	1.0
3.7003	48.0	240	3.4505	1.0
3.6903	54.0	270	3.4273	1.0
3.6331	60.0	300	3.4146	1.0

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2