torch-asgAuto Segmentation Criterion (ASG) implemented in pytorch
spokestack-androidExtensible Android mobile voice framework: wakeword, ASR, NLU, and TTS. Easily add voice to any Android app!
kosrKorean speech recognition based on transformer (트랜스포머 기반 한국어 음성 인식)
simple diarizerSimplified diarization pipeline using some pretrained models - audio file to diarized segments in a few lines of code
kaldi-allignerscripts to align a given wave to its transcription using trained models by Kaldi
lightning-asrModular and extensible speech recognition library leveraging pytorch-lightning and hydra.
opensnipsOpen source projects related to Snips https://snips.ai/.
speech-transformerTransformer implementation speciaized in speech recognition tasks using Pytorch.
torchainWIP: pytorch FFI wrapper for Kaldi chain loss (a.k.a. Lattice Free MMI)
syn-speech-samplesAn application that demostrate the usage of Syn.Speech library for Speech Recognition
wenetProduction First and Production Ready End-to-End Speech Recognition Toolkit
klaamArabic speech recognition, classification and text-to-speech.
rustfstRust re-implementation of OpenFST - library for constructing, combining, optimizing, and searching weighted finite-state transducers (FSTs). A Python binding is also available.
PCPMPresenting Collection of Pretrained Models. Links to pretrained models in NLP and voice.
KoLMKorean text normalization and language preparation package for LM in Kaldi-based ASR system
ctc-asrEnd-to-end trained speech recognition system, based on RNNs and the connectionist temporal classification (CTC) cost function.
kospeechOpen-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.
AESRC2020Data preperation scripts, training pipeline and baseline experiment results for the Interspeech 2020 Accented English Speech Recognition Challenge (AESRC).
avsr-tf1Audio-Visual Speech Recognition using Sequence to Sequence Models
myG2PMyanmar (Burmese) Language Grapheme to Phoneme (myG2P) Conversion Dictionary for speech recognition (ASR) and speech synthesis (TTS).
opensource-voice-toolsA repo listing known open source voice tools, ordered by where they sit in the voice stack
ASR-Audio-Data-LinksA list of publically available audio data that anyone can download for ASR or other speech activities
asr2424-hour Automatic Speech Recognition
wav2vec2-liveA live speech recognition using Facebooks wav2vec 2.0 model.
leopardOn-device speech-to-text engine powered by deep learning
megsA merged version of multiple open-source German speech datasets.
rasrThe RWTH ASR Toolkit.