Evaluate your speech-to-text system with similarity measures such as word error rate (WER)
-
Updated
Nov 1, 2024 - Python
#
word-error-rate
Here are 25 public repositories matching this topic...
An efficient OpenFST-based tool for calculating WER and aligning two transcript sequences.
-
Updated
Dec 10, 2024 - C++
STT 한글 문장 인식기 출력 스크립트의 외자 오류율(CER), 단어 오류율(WER)을 계산하는 Python 함수 패키지
aws amazon test speech-recognition 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
Aug 25, 2023 - Python
Evaluate results from ASR/Speech-to-Text quickly
diff statistics evaluation comparison speech-recognition accuracy words speech-to-text stt difference asr mismatches wer word-error-rate transcriptions punctuations insertions
-
Updated
Dec 28, 2021 - JavaScript
Calculates the word error rate of two strings, and the result is written into beautify HTML.
-
Updated
Mar 19, 2020 - Python
Takes audio and reference transcriptions in bulk and generates WER
-
Updated
Aug 9, 2021 - Python
🐍📦 Rapidly calculate and analyze the Word Error Rate (WER) with this powerful yet lightweight Python package.
python nlp metrics pandas levenshtein-distance automatic-speech-recognition speech-to-text stt asr python-package wer word-error-rate stt-benchmark asr-evaluation
-
Updated
Aug 12, 2024 - Python
Python tools to compare output transcript to reference
-
Updated
Jul 14, 2021 - 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Implementation of a couple of heuristics that estimate OCR quality without reliance on ground truth data, focusing on historical documents written in English.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
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.
python ai voice pytorch artificial-intelligence voice-recognition speech-recognition openai automatic-speech-recognition speech-to-text whisper marathi asr voice-assistant wer word-error-rate huggingface marathi-language trasnformers gopiashokan
-
Updated
Jan 29, 2024 - Jupyter Notebook
A word error rate util for golang
-
Updated
Nov 14, 2020 - Go
Word Error Rate computation using components from huggingface-evaluate and openai-whisper projects
-
Updated
Jan 9, 2024 - Python
Calculates the word error rate between the reference and hypothesis in ASR, then print the aligned result.
-
Updated
Jun 24, 2024 - C++
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
d-ser-t quantifies speech recognition accuracy of the MSFT speech service and/or user created MSFT custom speech service models.
-
Updated
Jan 4, 2023 - TypeScript
Exploring the functionality of the werpy Python package through testing within the Gradio tool for interactive user interface development.
-
Updated
Nov 29, 2023 - Python
Automatic Subtitle Generation for Bengali Multimedia Using Deep Learning.
deep-neural-networks deep-learning automatic-speech-recognition transcription fine-tuning word-error-rate state-of-the-art bengali-nlp timecode-generator wav2vec2 character-error-rate common-voice-dataset subtitle-generation bengali-subtitle-generation bengali-audio machine-generated-subtitle
-
Updated
Oct 29, 2023 - Jupyter Notebook
Small utility which helps to get most important metrics for STT
-
Updated
Feb 8, 2019 - C#
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."