wangershi / compareCTCDecoder
compare three CTC decoder, that is greedy decoder, beam decoder and prefix beam decoder
☆20Updated 6 years ago
Alternatives and similar repositories for compareCTCDecoder:
Users that are interested in compareCTCDecoder are comparing it to the libraries listed below
- magicspeech competition recipe☆18Updated 4 years ago
- CTC+Beam_Search+kenlm 是用于以汉字为声学模型建模单元的解码系统☆46Updated 6 years ago
- Kaldi extended by Kaituo XU with new features in nnet1.☆12Updated 6 years ago
- Conversion of recurrent neural network language models to weighted finite state transducers☆55Updated 6 years ago
- ☆9Updated 6 years ago
- ☆41Updated 6 years ago
- Example implementation of Monotonic Chunkwise Attention.☆51Updated 6 years ago
- A Python interface to OpenFst (fix FstDrawer interface issue for 1.6 version)☆17Updated 6 years ago
- LSTM CTC End2End Speech Recognition.☆38Updated 5 years ago
- An implementation of rnn transducer for sequence labeling problem☆22Updated 6 years ago
- ChiNese Text Normalization (CNTN) tool for Text-to-speech system☆35Updated 6 years ago
- Tensorflow version of DFSMN☆49Updated 6 years ago
- pytorch CTC implementation for ASR. Use eesen's fst decoder framework☆10Updated 4 years ago
- ☆16Updated 5 years ago
- Feedforward Sequential Memory Networks (FSMN) implemented by tensorflow☆50Updated 8 years ago
- ☆13Updated 7 years ago
- 以音素建模构建NN-CTC声学模型☆15Updated 5 years ago
- Recurrent Neural Aligner☆49Updated 4 years ago
- ☆55Updated 4 years ago
- A KALDI/C++ implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition☆14Updated 5 years ago
- Multiobjective Optimization Training of PLDA for Speaker Verification☆10Updated 6 years ago
- Code for the paper: Deep Residual Networks with Auditory Inspired Features for Robust Speech Recognition.☆21Updated 7 years ago
- Region proposal network based small-footprint keyword spotting (Pytorch)☆54Updated last year
- This is now the official location of the Kaldi project.☆22Updated 5 years ago
- This is an extension of kaldi speech recognition software which allows to perform decoding of speech with hybrid word and phoneme graphs.…☆11Updated 5 years ago
- Transformer based ASR Engine.☆12Updated 3 years ago
- create CMakeLists.txt for kaldi☆20Updated 4 years ago
- ICASSP 2020 ESPnet-TTS: Merlin baseline system☆36Updated 5 years ago
- Minimize kaldi nnet3 chain decoder☆45Updated 5 years ago
- Latest SRILM = 1.7☆19Updated 8 years ago