phoneme2txt_v1 – AI Model by Yangtze-flowing | AlphaNeural AI

You can deploy this model and start earning money today!

Yangtze-flowing/
phoneme2txt_v1

like

0

text2text-generation

generated_from_trainer

google-t5/t5-small

text-generation-inference

endpoints_compatible

Views

No views yet

phoneme2txt_v1

This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.2235
Bleu: 0.1130

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: 2e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
No log	1.0	111	4.3038	0.0718
No log	2.0	222	3.7919	0.1353
No log	3.0	333	3.5568	0.1129
No log	4.0	444	3.4293	0.0969
2.8297	5.0	555	3.3493	0.0944
2.8297	6.0	666	3.2983	0.0964
2.8297	7.0	777	3.2607	0.1078
2.8297	8.0	888	3.2399	0.1143
2.8297	9.0	999	3.2274	0.1114
2.1097	10.0	1110	3.2235	0.1130

Framework versions

Transformers 4.37.2
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.15.1