Evaluate your speech-to-text system with similarity measures such as word error rate (WER)
-
Updated
Feb 15, 2025 - Python
#
word-error-rate
Here are 13 public repositories matching this topic...
STT 한글 문장 인식기 출력 스크립트의 외자 오류율(CER), 단어 오류율(WER)을 계산하는 Python 함수 패키지
aws amazon test speech-recognition openai korean speech-to-text evaluation-functions evaluation-metrics normalization cer transcribe evaluate speech-analysis wer word-error-rate text-evaluation text-digitisation character-error-rate computing-error-rates
-
Updated
Jun 18, 2025 - Python
Calculates the word error rate of two strings, and the result is written into beautify HTML.
-
Updated
Mar 19, 2020 - Python
🐍📦 Ultra-fast Python package for calculating and analyzing the Word Error Rate (WER). Built for the scalable evaluation of speech and transcription accuracy.
python nlp metrics levenshtein-distance automatic-speech-recognition speech-to-text stt asr python-package wer word-error-rate stt-benchmark asr-evaluation werpy
-
Updated
Dec 8, 2025 - Python
Python tools to compare output transcript to reference
-
Updated
Jul 14, 2021 - Python
🐍📦 Easy-to-use Python package for lightning-fast Word Error Rate (WER) analysis
metrics levenshtein-distance automatic-speech-recognition speech-to-text stt asr wer word-error-rate werx python-rust
-
Updated
May 19, 2025 - Python
A simple Python package to calculate word error rate (WER).
-
Updated
Feb 7, 2021 - Python
Implementation of a couple of heuristics that estimate OCR quality without reliance on ground truth data, focusing on historical documents written in English.
-
Updated
Jun 2, 2023 - Python
Toolkit for using Whisper to transcribe YouTube videos. Includes Whisper transcription of YouTube videos, conversion of YouTube video into HuggingFace dataset (using audio and subtitles) and evaluation of Whisper transcription against YouTube subtitles
-
Updated
Oct 21, 2024 - Python
Exploring the functionality of the werpy Python package through testing within the Gradio tool for interactive user interface development.
-
Updated
Mar 21, 2025 - Python
ASR-LE is an advanced ASR evaluation + observability toolkit that goes beyond WER: it shows where errors happen in time, estimates streaming p95 first-word latency, generates “worst moments” automatically, and produces reusable artifacts (report.json, timeline bins, moments, etc.)
streaming latency speech-recognition automatic-speech-recognition speech-to-text whisper audio-processing asr ctc error-analysis word-error-rate mlops streamlit faster-whisper word-error-rate-calculator
-
Updated
Nov 28, 2025 - Python
Phonetic Fidelity Voice Conversion evaluates how well voice conversion models preserve phonetic details by comparing source and converted speech using Phoneme Error Rate (PER), complementing traditional text-based metrics like WER and CER
ffmpeg levenshtein-distance voice-conversion phonemes word-error-rate character-error-rate mozilla-common-voice seed-vc diff-hiervc vec2wav2 phoneme-error-rate multilingual-librispeech wav2vec2-large-xlsr-open-brazilian-portuguese-v2 wav2vec2-large-xlsr-53-phoneme-portuguese
-
Updated
Dec 2, 2025 - Python
Calculate the word error rate (WER) from provided correct and actual text file(s), for measuring the accuracy of automated speech recognition systems.
-
Updated
Jun 2, 2025 - Python
Improve this page
Add a description, image, and links to the word-error-rate topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the word-error-rate topic, visit your repo's landing page and select "manage topics."