txt2emovec

概要

txt2emovec (txt to emotion vector)
ユーザー入力を一度ずつtxt2emovecに食わせて8要素(喜び, 悲しみ, 期待, 驚き, 怒り, 恐怖, 嫌悪, 信頼)のベクトルに変換するためのモデル
talknizer: tohoku-nlp/bert-base-japanese-whole-word-masking
dataset: ids-cv/wrime のwrime-ver1.tsv

version

v0.0: 2024/11/13: データセットがwrime-v1のみということもあり、データに偏りがあるようで、予測精度もそれなり

Downloads last month: 30

Safetensors

Model size

111M params

Tensor type

F32

Inference Examples

Text Classification

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for sode-k/txt2emovec_ja

Base model

tohoku-nlp/bert-base-japanese-whole-word-masking

Finetuned

(4)

this model