t5_phoneme_decoder

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

t5_phoneme_decoder

This model is a fine-tuned version of t5-small on the Neural Prosthesis Phoneme-Text dataset. It achieves the following results on the evaluation set:

• Loss: 0.0892

Model description

This model accepts phoneme text sequences and decodes them into full sentences. In this case, phoneme sequences are generated by decoding neural spike data with a GRU based decoder. This model allows us to see the phonemes more naturally as English language.

Intended uses & limitations

This model was trained for a course project for ECE243 at UCLA. This is not intended for any other uses, besides for this project/future personal experimentation

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 12
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: polynomial
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.57.2
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1