Evaluate your speech-to-text system with similarity measures such as word error rate (WER)

An efficient OpenFST-based tool for calculating WER and aligning two transcript sequences.

STT 한글 문장 인식기 출력 스크립트의 외자 오류율(CER), 단어 오류율(WER)을 계산하는 Python 함수 패키지

Evaluate results from ASR/Speech-to-Text quickly

Calculates the word error rate of two strings, and the result is written into beautify HTML.

Takes audio and reference transcriptions in bulk and generates WER

🐍📦 Ultra-fast Python package for calculating and analyzing the Word Error Rate (WER). Built for the scalable evaluation of speech and transcription accuracy.

Python tools to compare output transcript to reference

A simple Python package to calculate word error rate (WER).

🐍📦 Easy-to-use Python package for lightning-fast Word Error Rate analysis

Implementation of a couple of heuristics that estimate OCR quality without reliance on ground truth data, focusing on historical documents written in English.

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

A word error rate util for golang

Developed a Marathi speech-to-text application using the Hugging Face whisper ASR models. Trained the model with a custom audio dataset and fine-tuned it for optimized performance. Deployed the model on the Hugging Face Model Hub, achieving a WER of 0.74 for the base model.

d-ser-t quantifies speech recognition accuracy of the MSFT speech service and/or user created MSFT custom speech service models.

Word Error Rate computation using components from huggingface-evaluate and openai-whisper projects

CMU sphinx evaluation scripts

Calculates the word error rate between the reference and hypothesis in ASR, then print the aligned result.

Automatic Subtitle Generation for Bengali Multimedia Using Deep Learning.