wav2vec2-base-timit-demo-colab60

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: 3.1975
• Wer: 1.0

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: 60
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
5.5799	7.04	500	3.2484	1.0
3.1859	14.08	1000	3.1951	1.0
3.1694	21.13	1500	3.1754	1.0
3.1637	28.17	2000	3.1818	1.0
3.1633	35.21	2500	3.1739	1.0
3.16	42.25	3000	3.2030	1.0
3.1602	49.3	3500	3.1974	1.0
3.1544	56.34	4000	3.1975	1.0

Framework versions

• Transformers 4.11.3
• Pytorch 1.11.0+cu113
• Datasets 1.18.3
• Tokenizers 0.10.3