Small utility which helps to get most important metrics for STT

CMU sphinx evaluation scripts

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

A word error rate util for golang

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

Python tools to compare output transcript to reference

Takes audio and reference transcriptions in bulk and generates WER

Evaluate results from ASR/Speech-to-Text quickly

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

Implementation of a couple of heuristics that estimate OCR quality without reliance on ground truth data, focusing on historical documents written in English.

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

Automatic Subtitle Generation for Bengali Multimedia Using Deep Learning.

Exploring the functionality of the werpy Python package through testing within the Gradio tool for interactive user interface development.

Evaluating the werpy Python package for UI development by testing it within PyScript for seamless integration and user interface exploration

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

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.

This study addresses the gap in translating Bangla regional dialects into standard Bangla by creating a large-scale multilingual benchmark dataset of 32,500 sentences in Bangla, Banglish, and English, representing five regional Bangla dialects such as Sylheti, Chittagong, Mymensingh, Noakhali, and Barishal.

Calculate the word error rate (WER) from provided correct and actual text file(s), for measuring the accuracy of automated speech recognition systems.

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