parlance/ctcdecode
PyTorch CTC Decoder bindings
When you're building a system that transcribes audio to text or recognizes other sequential data, you need to convert your model's raw predictions into meaningful outputs. This tool takes the probability outputs from your sequence model, along with your defined set of labels (like alphabet characters), and produces the most likely text sequences. It's for researchers and engineers developing speech recognition, handwriting recognition, or similar sequence-to-sequence models.
856 stars. No commits in the last 6 months.
Use this if you need to transform the raw outputs of a deep learning model into a coherent sequence of tokens or text, especially in speech or handwriting recognition applications.
Not ideal if you're looking for an off-the-shelf, end-user application for speech-to-text; this is a component for building such systems.
Stars
856
Forks
253
Language
C++
License
MIT
Category
Last pushed
Apr 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/parlance/ctcdecode"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
JaidedAI/EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin,...
breezedeus/CnSTD
CnSTD: 基于 PyTorch/MXNet 的 中文/英文 场景文字检测（Scene Text Detection）、数学公式检测（Mathematical Formula...
githubharald/SimpleHTR
Handwritten Text Recognition (HTR) system implemented with TensorFlow.
felixdittrich92/OnnxTR
OnnxTR a docTR (Document Text Recognition) library Onnx pipeline wrapper - for seamless,...
mindee/doctr
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for...