I'm Vladimir Gurevich, ML/NLP Engineer (IR tasks, such as Semantic Search, Information Extraction tasks, such as NER, Relation Extraction, etc.).
I am also interested in Speech Recognition and in LLMs.jupyter-notebook-viewer- Jupyter Notebook Viewer for local files *.ipynb in browser without Jupyter Notebook installation.wav2vec2-hebrew- package for speech recognition in Hebrew language using wav2vec2 models that were trained on Hebrew datasets (check out the datasets below).distiller- distillation TextClassification and TokenClassification models using transformers library with different distillation methods.spacy-trankit- spacy wrapper for Trankit (NLP pipeline for tokenization+dependency parsing+lemmatization, etc.)
t5-english-ner- NER model that based on T5 encoder that was trained on extremely small dataset.sentence-transformers-alephbert- Sentence Transformers model that based on AlephBERT model for sentence similarity tasks.het5_small_summarization- mt5-small based summarization model for Hebrew
wav2vec2-large-xlsr-53-hebrewwav2vec2-xls-r-300m-hebrewwav2vec2-xls-r-300m-lm-hebrewwav2vec2-xls-r-1b-hebrew
Speech Recognition Dataset for Hebrew (kan)Speech Recognition Dataset for Hebrew (coursera)Speech Recognition Dataset for Hebrew (campus)
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent