Yuriy Perezhohin's picture

Building on HF

Yuriy Perezhohin PRO

yuriyvnv

·

https://scholar.google.com/citations?user=I5uzFtwAAAAJ&hl=en

AI & ML interests

Automatic Speech Recognition, Embeddings, Code Generation, Synthetic Data Generation and Filtering

Recent Activity

posted an update 1 day ago

📄 The WAVe paper is officially out in the Information Sciences Journal. You saw the PT and NL model releases earlier this year. This is the peer-reviewed paper behind them, with the full method, ablations, and downstream ASR evaluation. Quick recap: WAVe is a 1B multimodal embedding model that filters synthetic speech at the word level, not the sentence level. On Portuguese ASR it cuts training steps by 34%, improves cross-domain generalization by 50%, and matches WER with 30% less synthetic data. 📦 Resources - Paper: https://www.sciencedirect.com/science/article/pii/S0020025526005220 - PT model: https://huggingface.co/yuriyvnv/WAVe-1B-Multimodal-PT - NL model: https://huggingface.co/yuriyvnv/WAVe-1B-Multimodal-NL - Collection: https://huggingface.co/collections/yuriyvnv/multi-modal-embeddings-for-synthetic-transcript-filtering - Code: https://github.com/yuriyvnv/WAVe If you train ASR on synthetic or back-translated data, would like to see WAVe benchmarked on other languages. @reach-vb @ylacombe @hf-audio @BramVanroy #speech #asr #multimodal #syntheticdata #lowresource

updated a collection 1 day ago

Multi-Modal Embeddings for Synthetic Transcript Filtering

updated a collection 1 day ago

Multi-Modal Embeddings for Synthetic Transcript Filtering

View all activity

Organizations

yuriyvnv 's collections 5