Pinned Repositories
tidylex
Tidy lexicographical data in backslash-coded formats
vad-sli-asr
A pipeline to isolate and transcribe one language in mixed-language speech
vyov
Visualise your own vowels: A short introduction to Praat for complete beginners
yinarlingi
R package for testing Warlpiri dictionary data structures
bnf_cnn_qbe-std
Query by example spoken term detection using bottleneck features and a convolutional neural network
fastconformer_standalone
qbe-std_feats_eval
Evaluation of feature extraction methods for query-by-example spoken term detection with low resource languages
wav2vec2-codebook-indices
qbestdocks
A set of pre-configured Docker containers for deploying a Query-by-Example Spoken Term Detection service.
fauxneticien's Repositories
fauxneticien/fastconformer_standalone
fauxneticien/wav2vec2-codebook-indices
fauxneticien/lnl-examples
PyTorch Lightning and Lhotse examples
fauxneticien/phd-dissertation
fauxneticien/PTL2-DS2ish
A toy repository for using PyTorch Lightning 2.x to train an adapted DeepSpeech 2 model
fauxneticien/scriptable_hubert_encoder
Development repository for experimenting with a scriptable (and crammable) HuBERT encoder
fauxneticien/ssl-harness
fauxneticien/w2v2-10min-exps
Experiments with wav2vec 2.0 models involving only 10 minutes of transcribed speech
fauxneticien/w2v2-batch-size
Code for paper "The effect of batch size on contrastive self-supervised speech representation learning"
fauxneticien/w2v2-cpt-transfer
fauxneticien/asr-dataset-prep
Scripts for preparing datasets for automatic speech recognition
fauxneticien/best-rq-pytorch
Implementation of BEST-RQ - a model for self-supervised learning of speech signals using a random projection quantizer, in Pytorch.
fauxneticien/BigVGAN
Official PyTorch implementation of BigVGAN (ICLR 2023)
fauxneticien/byt5-mt
fauxneticien/conformer
Implementation of the convolutional module from the Conformer paper, for use in Transformers
fauxneticien/ctc_decoder_files
fauxneticien/E2E-language-diarization-transfer
Source code of paper <End-to-End Language Diarization for Bilingual Code-switching Speech>
fauxneticien/fauxneticien
fauxneticien/fauxneticien.github.io
fauxneticien/hubert-exploration
fauxneticien/jupyter-book
Create beautiful, publication-quality books and documents from computational content.
fauxneticien/lightning-speech-sampling
Try out different samplers for speech data with PyTorch Lightning
fauxneticien/multi_quantization
fauxneticien/OPUS-MT-train
Training open neural machine translation models
fauxneticien/slasr-scripts
Data processing scripts for SLASR project
fauxneticien/w2v2-10min-replication
Replicate training wav2vec 2.0 model on just 10 minutes of Librispeech data
fauxneticien/w2v2-fairseq-pretrain
fauxneticien/w2v2-hf-pretrain-test
Testing wav2vec 2.0 pre-training with HuggingFace
fauxneticien/w2v2-pretrain-dynamic-batch
fauxneticien/Wav2vec2.0
Implementation of the paper "wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations" in Pytorch.