mxer / awesome-speech
this is a treasure-house of speech
☆164Updated 6 years ago
Alternatives and similar repositories for awesome-speech:
Users that are interested in awesome-speech are comparing it to the libraries listed below
- ASR for Chinese Mandarin☆75Updated 6 years ago
- End-to-end trained speech recognition system, based on RNNs and the connectionist temporal classification (CTC) cost function.☆122Updated 4 years ago
- Yet another speech toolkit based on Kaldi and PyTorch☆173Updated 4 years ago
- ☆106Updated 4 years ago
- ☆273Updated 4 years ago
- Seq2Seq Speech Recognition with Transformer on Mandarin Chinese☆116Updated 5 years ago
- Towards hot directions in industrial end to end speech recognition☆327Updated 3 years ago
- An LDA/PLDA estimator using KALDI in python for speaker verification tasks☆99Updated 7 years ago
- MXNet implementation of RNN Transducer (Graves 2012): Sequence Transduction with Recurrent Neural Networks☆139Updated 3 years ago
- PyTorch implementation of LF-MMI for End-to-end ASR☆220Updated 4 years ago
- ASR with PyTorch☆140Updated 6 years ago
- ☆142Updated 4 years ago
- A CRF-based ASR Toolkit☆329Updated 7 months ago
- Neural speaker recognition/verification system based on Kaldi and Tensorflow☆32Updated 4 years ago
- CN-Celeb, a large-scale Chinese celebrities dataset published by Center for Speech and Language Technology (CSLT) at Tsinghua University.☆72Updated 5 years ago
- A pytorch based end2end speech recognition system.☆112Updated 4 years ago
- Kaldi model converter to ONNX☆241Updated 2 years ago
- Implementation of state of the art d-vector approach for speaker verification☆127Updated 7 years ago
- CTC end -to-end ASR for timit and 863 corpus.☆217Updated 5 years ago
- A pure python module for reading and writing kaldi ark files☆252Updated last week
- A PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.☆200Updated 6 years ago
- A Pytorch Implementation of Transducer Model for End-to-End Speech Recognition☆232Updated 4 years ago
- DaCiDian is an open-sourced chinese mandarin lexicon for automatic speech recognition(ASR)☆301Updated 4 years ago
- A python module that convert chinese written string to read string. 一个python包:将中文书面字符串转换为口语字符串。☆119Updated 5 years ago
- 采用端到端方法构建声学模型,以字为建模单元,采用DCNN-CTC网络结构。☆71Updated 6 years ago
- INTERSPEECH 2019 Tutorial Materials☆193Updated 3 years ago
- Tensorflow implementation of x-vector topology on top of Kaldi recipe☆119Updated 5 years ago
- A statistical model-based Voice Activity Detection☆190Updated 6 years ago
- Share some recent speaker recognition papers and their implementations.☆90Updated 5 years ago
- Moved to https://github.com/k2-fsa/icefall☆144Updated 2 years ago