README.md

metadata

title: HTER
emoji: 🤗
colorFrom: blue
colorTo: red
sdk: gradio
sdk_version: 3.19.1
app_file: app.py
pinned: false
tags:
  - evaluate
  - metric
description: >-
  HTER (Half Total Error Rate) is a metric that combines the False Accept Rate
  (FAR) and False Reject Rate (FRR) to provide a comprehensive evaluation of a
  system's performance. It can be computed with: HTER = (FAR + FRR) / 2 Where:
  FAR (False Accept Rate) = FP / (FP + TN) FRR (False Reject Rate) = FN / (FN +
  TP) TP: True positive TN: True negative FP: False positive FN: False negative

Metric Card for HTER

Metric Description

HTER (Half Total Error Rate) is a metric that combines the False Accept Rate (FAR) and False Reject Rate (FRR) to provide a comprehensive evaluation of a system's performance. It can be computed with:

HTER = (FAR + FRR) / 2

Where:

FAR (False Accept Rate) = FP / (FP + TN)

FRR (False Reject Rate) = FN / (FN + TP)

TP: True positive

TN: True negative

FP: False positive

FN: False negative

How to Use

At minimum, this metric requires predictions and references as inputs.

>>> hter_metric = evaluate.load("murinj/hter")
>>> results = hter_metric.compute(references=[0, 0], predictions=[0, 1])
>>> print(results)
{'HTER': 0.25}

Inputs

• predictions (list of int): Predicted labels.
• references (list of int): Ground truth labels.

Output Values

• HTER(float or int): HTER score. Minimum possible value is 0. Maximum possible value is 1.0.

Output Example(s):

{'HTER': 0.0}

This metric outputs a dictionary, containing the HTER score.

Further References