wav2vec2-base-timit-demo-colab

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: 0.4545
• Wer: 0.3450

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: 32
• 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: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.3801	4.0	500	1.1501	0.8820
0.561	8.0	1000	0.4583	0.4211
0.2198	12.0	1500	0.4467	0.3997
0.1255	16.0	2000	0.4390	0.3677
0.0862	20.0	2500	0.4934	0.3603
0.0617	24.0	3000	0.4641	0.3549
0.0465	28.0	3500	0.4545	0.3450

Framework versions

• Transformers 4.11.3
• Pytorch 1.10.0+cu111
• Datasets 1.18.3
• Tokenizers 0.10.3