Search Packages

tensorflowasr

:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords

ctc-forced-aligner

We are open-sourcing the CTC forced aligner used in Deskpai. With focus on production-ready model inference, it supports 18 different alignment models, including multilingual models(German, English, Spanish, French and Italian etc), and provides SRT and WebVTT alignment and generation out of box. Onnxruntime and PyTorch are supported.

ctcdecode

PyTorch CTC Decoder bindings

k2-sherpa

Speech-to-text server framework with next-gen Kaldi

thulium-htr

Thulium is a production-ready Python library for offline handwritten text recognition (HTR) supporting 52+ languages across Latin, Cyrillic, Greek, Arabic, Hebrew, Devanagari, Chinese, Japanese, Korean, and Georgian scripts.

ctcdecodeupd

PyTorch CTC Decoder bindings

asrt

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统