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: 0.4520
• Wer: 0.2286

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
3.3811	4.0	500	1.1887	0.8528
0.5798	8.0	1000	0.4544	0.3357
0.2197	12.0	1500	0.4424	0.2699
0.1279	16.0	2000	0.4388	0.2559
0.0855	20.0	2500	0.4572	0.2450
0.062	24.0	3000	0.4385	0.2353
0.0469	28.0	3500	0.4520	0.2286

Framework versions

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