wav2vec2-base_toy_train_data_random_low_pass

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: 1.3227
• Wer: 0.7288

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
• 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: 1000
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.0795	2.1	500	3.2227	0.9982
1.21	4.2	1000	1.3713	0.8879
0.742	6.3	1500	1.2660	0.8296
0.5877	8.4	2000	1.2921	0.7794
0.4823	10.5	2500	1.2899	0.7565
0.4036	12.6	3000	1.3486	0.7494
0.391	14.7	3500	1.2701	0.7466
0.3426	16.81	4000	1.3570	0.7279
0.3015	18.91	4500	1.3227	0.7288

Framework versions

• Transformers 4.17.0
• Pytorch 1.11.0+cu102
• Datasets 2.0.0
• Tokenizers 0.11.6