OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Evaluation & Observability

Asr Evaluation

Asr Evaluation is a Python module and command-line tool for comparing automatic speech recognition hypothesis transcripts with reference transcripts. It reports word error rate, word recognition rate and sentence error rate, and can display sentence-level errors, word confusions and average WER grouped by reference sentence length.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Asr Evaluation — OpenViST project profile in AI Evaluation & Observability.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when reference transcripts are available and you need quantitative measures or diagnostic reports on ASR hypothesis text.

Who it is for

  • Developers or evaluators comparing ASR output with reference transcripts.
  • Teams investigating which sentences or words contribute to recognition errors.

Documented uses

  • Calculate WER, word recognition rate and SER from reference and hypothesis files.
  • Inspect incorrect sentences and word-level confusions.
  • Compare average WER across reference sentence-length groups.
Before you choose

Requirements & limits

The project is an open-source Python repository under the Apache-2.0 license. The README documents pip installation and installation from a cloned repository.

  • Evaluation uses transcript files, not audio input.
  • The tool depends on the editdistance project for sequence edit-distance calculations.
  • Optional output includes individual sentence errors, word-confusion tables, and WER grouped by reference sentence length.
  • Options accommodate case-insensitive comparison, empty references, and IDs at the start or end of transcript lines.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the Python package and view CLI options

Install Asr Evaluation with pip and consult the command-line help before evaluating transcript files.

Before you start

  • Python package installation through pip.

Steps

  1. Install the package with the command below.

    Documented command
    pip install asr-evaluation

  2. Run wer --help to display the available command-line options.

Expected outcome

The package installation route and CLI options are documented; the help output describes the reference and hypothesis file arguments and available reporting flags.

Guide limitations

  • These steps cover installation and help only, not execution of an evaluation.
  • The README also documents a clone-and-distutils installation route.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
belambert/asr-evaluation · Official homepage title · retained in its source language
How we review sourcesSuggest a correction