wav2vec2-base_toy_train_data

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: 1.2522
• Wer: 0.7297

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.0033	4.2	500	2.7702	1.0
1.055	8.4	1000	1.2671	0.8667
0.6628	12.6	1500	1.1952	0.7883
0.5023	16.8	2000	1.1435	0.7659
0.4535	21.01	2500	1.1889	0.7458
0.3604	25.21	3000	1.2650	0.7378
0.3175	29.41	3500	1.2522	0.7297

Framework versions

• Transformers 4.18.0
• Pytorch 1.11.0+cu102
• Datasets 2.1.0
• Tokenizers 0.12.1