janinerugayan

AESRC2020

Data preperation scripts, training pipeline and baseline experiment results for the Interspeech 2020 Accented English Speech Recognition Challenge (AESRC).

aligned-semantic-distance

asv-subtools

An Open Source Tools for Speaker Recognition

Autoregressive-Predictive-Coding

Autoregressive Predictive Coding: An unsupervised autoregressive model for speech representation learning

beamerthementnu

A LaTeX beamer theme for presentations in the NTNU corporate design

CE-OptimizedLoss

Optimized loss based on cross-entropy (CE), like MWER (minimum WER) Loss with beam search and negative sampling strategy, Smoothed Max Pooling Loss.

CTC-OptimizedLoss

Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.

DT8807

fine-tuning-wav2vec2-NO

fine-tuning-whisper-NO

fine-tuning whisper model for Norwegian

janinerugayan/aligned-semantic-distance

janinerugayan/AESRC2020

Data preperation scripts, training pipeline and baseline experiment results for the Interspeech 2020 Accented English Speech Recognition Challenge (AESRC).

janinerugayan/asv-subtools

An Open Source Tools for Speaker Recognition

janinerugayan/Autoregressive-Predictive-Coding

Autoregressive Predictive Coding: An unsupervised autoregressive model for speech representation learning

janinerugayan/beamerthementnu

A LaTeX beamer theme for presentations in the NTNU corporate design

janinerugayan/CE-OptimizedLoss

Optimized loss based on cross-entropy (CE), like MWER (minimum WER) Loss with beam search and negative sampling strategy, Smoothed Max Pooling Loss.

janinerugayan/CTC-OptimizedLoss

Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.

janinerugayan/DT8807

janinerugayan/fine-tuning-wav2vec2-NO

janinerugayan/fine-tuning-whisper-NO

fine-tuning whisper model for Norwegian

janinerugayan/kaldi

kaldi-asr/kaldi is the official location of the Kaldi project.

janinerugayan/masterthesis

janinerugayan/MOSNet

Implementation of "MOSNet: Deep Learning based Objective Assessment for Voice Conversion"

janinerugayan/NorBERT

Large-scale language models for Norwegian

janinerugayan/norec_sentence

Aggregated datasets for sentence-level sentiment classification in Norwegian

janinerugayan/py-lbg

Python Implementation for Linde-Buzo-Gray / Generalized Lloyd Algorithm for vector quantization.

janinerugayan/pyctcdecode

A fast and lightweight python-based CTC beam search decoder for speech recognition.

janinerugayan/rVAD

Matlab and Python libraries for an unsupervised method for robust voice activity detection (rVAD), as in the paper rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method.

janinerugayan/speechbrain

A PyTorch-based Speech Toolkit

janinerugayan/spolacq

unofficial fork

janinerugayan/stanford-ctc

Neural net code for lexicon-free speech recognition with connectionist temporal classification

janinerugayan/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

janinerugayan/Vector-Quantization---LBG

Python Implementation of Vector Quantization with Linde–Buzo–Gray algorithm

janinerugayan/VectorQuantizedCPC

Vector-Quantized Contrastive Predictive Coding for Acoustic Unit Discovery and Voice Conversion

janinerugayan/VQ-APC

Vector Quantized Autoregressive Predictive Coding (VQ-APC)

janinerugayan/ZeroSpeech

VQ-VAE for Acoustic Unit Discovery and Voice Conversion