Tag
ai-models
20 posts · all tags
29 Cheshvan 5787
Meorav: speech synthesis for English-Hebrew code-switching
Meorav is my text-to-speech model for English with Hebrew words dropped in, the way English speakers in Israel talk. Irish accent included. v2.2 is a Qwen3-TTS fine-tune on 5.5 hours of my voice. Before and after samples.
28 Cheshvan 5787 Update
Fritter v1.3, a vocabulary cloud and a public tracker
Fritter, my English dictation fine-tune for tech vocabulary, is at v1.3. The demo now opens with a moving cloud of the real terms it was trained on, and the project has a public tracker repo.
26 Cheshvan 5787 Update
Fritter gets a streaming version and direct downloads
Fritter, my English dictation fine-tune for technical vocabulary, is at v1.2 with a first streaming version. Both now download directly from plain URLs, and here is how it differs from my code-switching model.
23 Cheshvan 5787
Contextual Sentence Creator: a 3B model that writes ASR training sentences
A Granite 4.2 3B fine-tune that writes natural sentences using a given term, for recording speech recognition training data. 95.7% of sentences pass the acceptance check; GGUF build included.
23 Cheshvan 5787
Fritter: a Parakeet fine-tune for English tech dictation
Fritter is my Parakeet TDT 0.6B v2 fine-tune for English dictation without Hebrew: tech terms, numbers and brand names. Tech WER falls from 7.53% to 4.01% on my voice. Browser demo and GGUF builds.
23 Cheshvan 5787
Hey Yossi: a custom wake word for Home Assistant
Hey Yossi is a custom wake word for Home Assistant, trained on real recordings, in two builds: openWakeWord for the server and Pi, microWakeWord for ESPHome, Voice PE and Android. 95% recall in testing.
23 Cheshvan 5787
S1-ASR-Cleanup: cleaning up dictation with a fine-tuned S1-mini
A fine-tune of S1-mini by Superwhisper that cleans speech-to-text dictation: paragraphs, dates and money as digits, contractions and fillers handled. 0.6B, with GGUF builds for llama.cpp and phones.
23 Cheshvan 5787 Update
Update: a 32 MB model for ASR paragraph breaks
MiniLM-L12-ASR-Paragraph-Breaks replaces my Gemma 3 270M paragraph model: break F1 0.85 against 0.78, 32 MB instead of 437 MB, and it cannot change a word of the transcript.
23 Cheshvan 5787
Agent Task Break Detector: knowing when to start a fresh session
A small ModernBERT model that checks every message in an AI agent session and says whether it is a new task a fresh session could handle. Runs locally on CPU; v0.1, trained on synthetic data.
10 Cheshvan 5787
Adding paragraph breaks to speech-to-text output with Gemma 3 270M
A Gemma 3 270M fine-tune that adds paragraph breaks to flat speech-to-text output and changes nothing else. Small enough for on-device use, with an ONNX export. Break F1 0.78 on 26 held-out memos.
10 Cheshvan 5787
Bolding the key lines of a dictated email with Gemma 3 270M
A preliminary Gemma 3 270M fine-tune that bolds the key lines of a dictated email (the asks, the purpose, the key facts) and changes nothing else. Small enough for on-device use. Word F1 0.62 on six held-out emails.
10 Cheshvan 5787
Proximate Pseudonymizer: a small model that swaps identifying details for close substitutes
A proof-of-concept Qwen3-0.6B fine-tune that rewrites text with names, places and dates swapped for close, consistent substitutes (Daniel to David, Jerusalem to Tel Aviv). Runs on CPU. Still leaks 9.3% of details, so review every output.
9 Cheshvan 5787
Boxty v1.0: English dictation without the Hebrew
Boxty is the no-Hebrew sibling of my Jachnun code-switching model: Parakeet fine-tuned on my voice for plain English and tech dictation. Tech WER drops from 2.51% (stock) to 1.35%, and general English holds.
9 Cheshvan 5787
Do LLMs push back on conspiracy believers? A small first look
A small, hand-graded first look at my conspiracy-endorsement eval: 7 prompts, 7 models, one sample each. In this run two uncensored models helped a believer and an invented theory tripped up two more. Not a verdict on any model.
6 Cheshvan 5787 Update
Whisper Hebrish Small ACFT: a code-switching model for FUTO Keyboard
A phone-sized Whisper Hebrish for FUTO Keyboard on Android. It halves the stock English model's error rate on English-with-Hebrew dictation (11.8% to 5.8% WER) and imports as a single 264 MB file.
6 Cheshvan 5787 Update
Whisper Hebrish v2 Released
Version 2 of Whisper Hebrish, my Whisper fine-tune for English with Hebrew words mixed in. Code-switching WER drops from 14.7% (stock turbo) to 6.7%, and there are whisper.cpp builds.
4 Cheshvan 5787 Update
inventory-spec-extractor: a 34 MB model for reading product spec lines
A small token-classification model that pulls voltages, connectors, materials and 22 other attributes out of one line of a product spec. Runs on CPU in about 20 ms per line. F1 0.85 against a regex baseline's 0.58.
4 Cheshvan 5787
My Hugging Face models and datasets, by theme (October 2026)
A point-in-time snapshot of the 16 models and 72 datasets on my Hugging Face profile, grouped by theme, from Hebrew-English code-switching to Jerusalem photography.
4 Cheshvan 5787
Teaching a podcast to say makolet: a classifier for Hebrew hiding in English
I released a small model on Hugging Face that finds romanised Hebrew words inside English text, so TTS voices like Chatterbox can stop reading them as English. Built for My Weird Prompts.
7 Nisan 5786
Fine-tuning Whisper on Modal's serverless GPUs
A script for fine-tuning OpenAI's Whisper speech recognition models using Modal's serverless GPU infrastructure.