poly-6

This model is a fine-tuned version of facebook/wav2vec2-base on the minds14 dataset. It achieves the following results on the evaluation set:

• Loss: 27.5287
• 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: 0.0003
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
15.5918	1.0	1	27.5287	1.0
15.5936	2.0	2	27.5287	1.0
15.6148	3.0	3	27.5287	1.0
15.6283	4.0	4	27.5287	1.0

Framework versions

• Transformers 4.40.2
• Pytorch 2.1.2+cpu
• Datasets 2.19.1
• Tokenizers 0.19.1