phoneme2txt_v0

Yangtze-flowing/phoneme2txt_v0

phoneme2txt_v0 is a machine learning model from Yangtze-flowing. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

14% of all-time downloads

All-time downloads

Public

Parameters

60.5M

968 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors242 MB · 99%

At a glance

Library: transformers
Model type: t5
Access: Public
Created: Nov 18, 2023
Updated: Nov 23, 2023
SHA: 29fa2629

Model card

From the Hugging Face model README

phoneme2txt_v0

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.5025
Bleu: 0.1925
Gen Len: 16.1667

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: 16
eval_batch_size: 16
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	Gen Len
No log	1.0	15	3.9690	0.0897	19.0
No log	2.0	30	3.8383	0.0894	19.0
No log	3.0	45	3.7403	0.0894	19.0
No log	4.0	60	3.6702	0.0	18.7667
No log	5.0	75	3.6162	0.1205	18.2667
No log	6.0	90	3.5742	0.1611	17.5833
No log	7.0	105	3.5432	0.1724	17.1
No log	8.0	120	3.5210	0.1872	16.7
No log	9.0	135	3.5080	0.1899	16.3333
No log	10.0	150	3.5025	0.1925	16.1667

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

Library: transformers
Type: t5
Created: Nov 18, 2023
Updated: Nov 23, 2023