Per von Rosen's repositories
bert_experimental
code and supplementary materials for a series of Medium articles about the BERT model
camel-kenlm
KenLM: Faster and Smaller Language Model Queries
CodeLM
A repo for code based language models
DeepFaceLab
DeepFaceLab is the leading software for creating deepfakes.
Dictionaries
Hunspell UTF8 dictionaries. These work with Sublime Text. [Spell check]
fastai-projects
Jupyter notebooks that use the Fastai library
istio-tutorial
Istio Tutorial for https://dn.dev/master
keras-punctuator
Experimental project to punctuate text using a embedding layer, single convolutional layer and output softmax layer written in Keras.
Knowledge-Distillation-Toolkit
A knowledge distillation toolkit based on PyTorch and PyTorch Lightning.
leech
Crawling capabilities for Apache Tika. Crawl content out of e.g. file systems, http(s) sources (webcrawling) imap(s) servers or your own arbitrary data sources. LeechCrawler offers additional Tika parsers providing these crawling capabilities.
punctuation-prediction
Support tools for punctuation and boundary detection for ASR output.
pytorch-qrnn
PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM
Resemblyzer
A python package to analyze and compare voices with deep learning
sentence-transformers
Sentence Embeddings with BERT & XLNet
solana-metamask-poc
Solana X Metamask Proof of Concept
swedish-ner
Swedish NER using my self-trained model based on FLAIR. Published through Streamlit.io.
Text-classification-for-long-text
Text Classification using transformer based models
vault-helpers
A collection of scripts to configure Hashicorp Vault.