E2e AsrPyTorch Implementations for End-to-End Automatic Speech Recognition
Stars: ✭ 106 (+430%)
EspressoEspresso: A Fast End-to-End Neural Speech Recognition Toolkit
Stars: ✭ 808 (+3940%)
kospeechOpen-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.
Stars: ✭ 456 (+2180%)
kosrKorean speech recognition based on transformer (트랜스포머 기반 한국어 음성 인식)
Stars: ✭ 25 (+25%)
Rnn TransducerMXNet implementation of RNN Transducer (Graves 2012): Sequence Transduction with Recurrent Neural Networks
Stars: ✭ 114 (+470%)
KospeechOpen-Source Toolkit for End-to-End Korean Automatic Speech Recognition.
Stars: ✭ 190 (+850%)
Keras SincnetKeras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)
Stars: ✭ 47 (+135%)
Asr benchmarkProgram to benchmark various speech recognition APIs
Stars: ✭ 71 (+255%)
Wav2letterSpeech Recognition model based off of FAIR research paper built using Pytorch.
Stars: ✭ 78 (+290%)
EesenThe official repository of the Eesen project
Stars: ✭ 738 (+3590%)
PykaldiA Python wrapper for Kaldi
Stars: ✭ 756 (+3680%)
opensource-voice-toolsA repo listing known open source voice tools, ordered by where they sit in the voice stack
Stars: ✭ 21 (+5%)
Syn SpeechSyn.Speech is a flexible speaker independent continuous speech recognition engine for Mono and .NET framework
Stars: ✭ 57 (+185%)
BigcidianPronunciation lexicon covering both English and Chinese languages for Automatic Speech Recognition.
Stars: ✭ 99 (+395%)
DeepspeechrecognitionA Chinese Deep Speech Recognition System 包括基于深度学习的声学模型和基于深度学习的语言模型
Stars: ✭ 1,421 (+7005%)
KtspeechcrawlerAutomatically constructing corpus for automatic speech recognition from YouTube videos
Stars: ✭ 92 (+360%)
Py Kaldi AsrSome simple wrappers around kaldi-asr intended to make using kaldi's (online) decoders as convenient as possible.
Stars: ✭ 156 (+680%)
Asr EvaluationPython module for evaluating ASR hypotheses (e.g. word error rate, word recognition rate).
Stars: ✭ 190 (+850%)
Transformer-TransducerPyTorch implementation of "Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss" (ICASSP 2020)
Stars: ✭ 61 (+205%)
speech-transformerTransformer implementation speciaized in speech recognition tasks using Pytorch.
Stars: ✭ 40 (+100%)
Speech-RecognitionEnd-to-end Automatic Speech Recognition for Madarian and English in Tensorflow
Stars: ✭ 21 (+5%)
Libreasr💬 An On-Premises, Streaming Speech Recognition System
Stars: ✭ 633 (+3065%)
WenetProduction First and Production Ready End-to-End Speech Recognition Toolkit
Stars: ✭ 617 (+2985%)
SincnetSincNet is a neural architecture for efficiently processing raw audio samples.
Stars: ✭ 764 (+3720%)
Athenaan open-source implementation of sequence-to-sequence based speech processing engine
Stars: ✭ 542 (+2610%)
ctc-asrEnd-to-end trained speech recognition system, based on RNNs and the connectionist temporal classification (CTC) cost function.
Stars: ✭ 112 (+460%)
OpenasrA pytorch based end2end speech recognition system.
Stars: ✭ 69 (+245%)
Silero ModelsSilero Models: pre-trained STT models and benchmarks made embarrassingly simple
Stars: ✭ 522 (+2510%)
DeltaDELTA is a deep learning based natural language and speech processing platform.
Stars: ✭ 1,479 (+7295%)
Vosk ApiOffline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
Stars: ✭ 1,357 (+6685%)
specAugmentTensor2tensor experiment with SpecAugment
Stars: ✭ 46 (+130%)
Asr audio data linksA list of publically available audio data that anyone can download for ASR or other speech activities
Stars: ✭ 128 (+540%)
Pytorch Kaldipytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
Stars: ✭ 2,097 (+10385%)
Asrt speechrecognitionA Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
Stars: ✭ 4,943 (+24615%)
Cn2an📦 快速转化「中文数字」和「阿拉伯数字」~ (最新特性:分数,日期、温度等转化)
Stars: ✭ 249 (+1145%)
ZerothKaldi-based Korean ASR (한국어 음성인식) open-source project
Stars: ✭ 248 (+1140%)
ASR-Audio-Data-LinksA list of publically available audio data that anyone can download for ASR or other speech activities
Stars: ✭ 179 (+795%)
wav2letterFacebook AI Research's Automatic Speech Recognition Toolkit
Stars: ✭ 6,026 (+30030%)
EspnetEnd-to-End Speech Processing Toolkit
Stars: ✭ 4,533 (+22565%)
Speech TransformerA PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.
Stars: ✭ 565 (+2725%)
wav2vec2-liveA live speech recognition using Facebooks wav2vec 2.0 model.
Stars: ✭ 205 (+925%)
EdgedictWorking online speech recognition based on RNN Transducer. ( Trained model release available in release )
Stars: ✭ 205 (+925%)
leopardOn-device speech-to-text engine powered by deep learning
Stars: ✭ 354 (+1670%)
NmtpytorchSequence-to-Sequence Framework in PyTorch
Stars: ✭ 392 (+1860%)
Neural spEnd-to-end ASR/LM implementation with PyTorch
Stars: ✭ 408 (+1940%)
LingvoLingvo
Stars: ✭ 2,361 (+11705%)
Wav2letterFacebook AI Research's Automatic Speech Recognition Toolkit
Stars: ✭ 5,907 (+29435%)
Listen Attend SpellA PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.
Stars: ✭ 147 (+635%)
megsA merged version of multiple open-source German speech datasets.
Stars: ✭ 21 (+5%)