oxinabox / Kaldi-NotesLinks
Some notes on Kaldi
☆31Updated 10 years ago
Alternatives and similar repositories for Kaldi-Notes
Users that are interested in Kaldi-Notes are comparing it to the libraries listed below
Sorting:
- Custom decoders for Kaldi☆79Updated 6 years ago
- An example directory for running Multi-Task Learning training on Kaldi neural networks. In Kaldi-speak, this is an egs dir for nnet3 trai…☆54Updated 5 years ago
- A python package that make tensorflow be able to read "Kaldi" scp/ark in an elegant way. May kaldi user happy to enter tensorflow world.☆40Updated 6 years ago
- ☆48Updated 4 years ago
- Conversion of recurrent neural network language models to weighted finite state transducers☆58Updated 7 years ago
- An implementation of rnn transducer for sequence labeling problem☆22Updated 7 years ago
- Open Source WFST-based Decoder Toolkit☆77Updated 9 years ago
- Small language toolkit for creation, interpolation and pruning of ARPA language models☆92Updated 3 years ago
- Long audio alignment using Kaldi☆23Updated 4 years ago
- Collection of machine learning demos for Automatic Speech Recognition☆55Updated 3 years ago
- Custom decoders for Kaldi☆13Updated 6 years ago
- This is now the official location of the Kaldi project.☆24Updated 5 years ago
- ☆16Updated 6 years ago
- Adapting your own Language Model for Kaldi☆63Updated 6 years ago
- ☆41Updated 7 years ago
- ☆76Updated 3 years ago
- Tensor2tensor experiment with SpecAugment☆46Updated 6 years ago
- Tutorial on Kaldi for Brandeis ASR course☆75Updated 5 years ago
- Use your data to create a speech recognition system in Kaldi. Fast.☆65Updated 5 years ago
- Meta-embeddings are a probabilistic generalization of embeddings in machine learning.☆22Updated 6 years ago
- Recurrent Neural Aligner☆50Updated 5 years ago
- ☆45Updated 6 years ago
- maracas is a library for corrupting audio files with additive and convolutive noise.☆72Updated 8 years ago
- Juicer is a Weighted Finite State Transducer (WFST) based decoder for Automatic Speech Recognition (ASR).☆62Updated 9 years ago
- Code for end-to-end ASR with neural networks, build with TensorFlow☆109Updated 6 years ago
- A KALDI/C++ implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition☆14Updated 6 years ago
- ☆58Updated 6 years ago
- Adapt Kaldi-ASR nnet3 chain models from Zamia-Speech.org to a different language model☆33Updated 5 years ago
- A Python interface to OpenFst (fix FstDrawer interface issue for 1.6 version)☆17Updated 7 years ago
- Voxceleb1 i-vector based speaker recognition system☆43Updated 7 years ago