wav2vec2-base-mscd1

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: 1.8065
• Wer: 0.3824

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: 300
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
6.6008	41.67	500	4.7974	1.0
1.2892	83.33	1000	1.7488	0.5
0.1991	125.0	1500	1.3122	0.4412
0.109	166.67	2000	1.3265	0.3235
0.071	208.33	2500	1.1280	0.3529
0.0508	250.0	3000	1.6514	0.3529
0.0365	291.67	3500	1.8065	0.3824

Framework versions

• Transformers 4.24.0
• Pytorch 2.0.0+cu118
• Datasets 1.18.3
• Tokenizers 0.13.3