wav2vec2-base-timit-demo-colab-test

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: 0.4283
• Wer: 0.3356

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
3.7386	4.0	500	2.2419	1.0
0.9366	8.0	1000	0.4789	0.4807
0.3118	12.0	1500	0.4197	0.3973
0.1784	16.0	2000	0.4216	0.3614
0.1297	20.0	2500	0.4298	0.3507
0.1091	24.0	3000	0.4365	0.3437
0.0819	28.0	3500	0.4283	0.3356

Framework versions

• Transformers 4.11.3
• Pytorch 1.10.0+cu111
• Datasets 1.13.3
• Tokenizers 0.10.3