AI · everything on Hugging Face

Hugging Face index

Every model, dataset, Space and collection I've published, from my account and the Hebrish organisation. Filter, search, and click through. Items with a card page on this site open there first.

41models
115datasets
68spaces
211collections

Start here: card pages

The main models and datasets have full pages on this site, with results, downloads and roadmap. Or see the models showcase.

ModelJachnun (Parakeet English–Hebrew code-switching)Speech-to-text that gets the Hebrew words right when an English speaker in Israel drops them into English: "pick up some bamba from the makolet".ModelSabich (Parakeet code-switching plus tech)The recommended Hebrish model: everything Jachnun was trained on, plus tech vocabulary, brand names, acronyms, numbers and currency, Irish-English phrasing and the rest of my task recordings.ModelBoxty (Parakeet English and tech dictation)English dictation without Hebrew, in my voice: model and product names, CLI and cloud terms, brands, acronyms, and numbers and currency in digits.ModelHebrew-Latin Token ClassifierFinds Hebrew words written in Latin letters inside English text, so text-to-speech can hand them to a Hebrew voice instead of reading makolet as English. There was no model for this before.ModelGemma 3 270M paragraph breaksAdds paragraph breaks to flat speech-to-text output and changes nothing else. Small enough to run on a phone after the speech model.ModelGemma 3 270M email key-line boldingPuts the key parts of a dictated email in Markdown bold and changes nothing else. Runs after the paragraph-breaks model.ModelProximate Pseudonymizer 0.6BRewrites a text with its names, places, organisations, dates and contacts swapped for close, plausible substitutes, the same one every time. Proof of concept: it still leaves 9.3% of identifying details unchanged.ModelSabich-Qwen3-ASR-1.7B (desktop GPU)The most accurate Sabich: the same code-switching and tech data, trained on Qwen3-ASR 1.7B, an ASR model with an LLM decoder, for computers with a GPU.ModelShakshuka (Nemotron streaming)The streaming line of Hebrish: text appears while you speak, trained on the same everything-in-it recordings as Sabich.DatasetEnglish–Hebrew Code-Switching SentencesEnglish sentences with everyday Hebrew words and Israeli names written in Latin letters, read aloud on a phone by one English speaker living in Israel.DatasetRead-Aloud Voice SentencesEvery take recorded for the Hebrish speech models: read-aloud English sentences with Hebrew words, tech vocabulary, names, emails and messages, recorded on a phone and published in batches straight from the capture app.DatasetEnglish–Hebrew Code-Switching ASR BenchmarkA frozen, versioned test set for scoring how well speech recognition writes the Hebrew words in English speech, "pick up some bamba from the makolet", with stock models and fine-tunes scored the same way on a public leaderboard.DatasetHebrew-in-Latin Code-Switching CorpusEnglish sentences with Hebrew words written in Latin letters, every Hebrew span marked token by token, for finding those words in text before text-to-speech mispronounces them. No corpus like it had been published.

Browse everything

My account's list refreshes daily. Hebrish items were fetched from Hugging Face when this page was built. Collections are mostly curated reading lists of other people's work.

Start here: card pages

Browse everything

Need speech AI, agent workflows or evals built for your team?