Aku Rouhe

A notebook that looks at results from HMM and AED ASR systems.

Speech Recognition experiments combining Lahjoita Puhetta with Finnish Parliament

Extensions to YAML syntax for better python interaction

Experimental UI course Aggregation server

Librispeech HMM/DNN SpeechBrain S5

SpeechBrain recipes for Finnish Parliament data - HMM/DNN

CAPT application

No description provided.

PyTorch implementation of LF-MMI for End-to-end ASR

A PyTorch-based Speech Toolkit

Properly handle position-dependent phones in a subword lexicon FST

No description provided.

TheanoLM is a recurrent neural network language modeling tool implemented using Theano

No description provided.

SpeechBrain continuous integration environment

No description provided.

Generate text with char-rnns. Specifically for continuing sentences in funny ways.

Create grammars which are able to follow reading based on the source text

Open Source Neural Machine Translation in PyTorch

No description provided.

Kaldi recipe for the Finnish Eduskunta data

Matlab implementation of the Warm Chorus algorithm by Richard Dudas, for an Audio signal processing course

No description provided.

*BeaqleJS* provides a framework to create browser based listening tests and is purely based on open web standards like HTML5 and Javascript.

Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.

No description provided.

This is now the official location of the Kaldi project.

Initially, copy the same capabilities as alumae/gst-kaldi-nnet2-online to GMM-decoding

Dockerfile for kaldi-gstreamer-server.

Create Kaldi-style datadirs for k-fold cross-validation