Daniel Rosehill PRO

danielrosehill

·

https://www.danielrosehill.com

AI & ML interests

Speech to text (ASR), voice workflows, MCP, AI agents, orchestration, automation.

Recent Activity

updated a dataset less than a minute ago

Hebrish/ASR-Error-List

updated a dataset 8 minutes ago

Hebrish/Irish-English-Sentences

updated a dataset 9 minutes ago

Hebrish/Acronym-Sentences

View all activity

Organizations

danielrosehill 's Spaces 67

Podcast ASR Evaluation

ASR benchmark comparing local and cloud models

OR Batch Inference Costs

OpenRouter batch model costs by price tier

English-Hebrew Code-Switching ASR Leaderboard

ASR on English speech with Hebrew words in it

ASR Dataset Blender

Blend speech datasets into NeMo training manifests

Try Fritter

Parakeet v2 fine-tune for tech dictation, in your browser

Using AI to Decide a Vote (Knesset 2026)

One voter's AI-built rubric scoring every 2026 Knesset list

Paragraph Inference for ASR

What paragraph inference is, and where it fits in ASR

Agent Task Break Detector

Does this message need the session so far, or a fresh one?

Knesset 2026 Decision-Model Forecast

Decision models forecast Israel's 2026 Knesset election

Me and My Voice Clone

A conversation between me and a TTS clone of my own voice

Proximate Pseudonymizer

Swap identifying details for close substitutes (PoC)

ASR Paragraph Breaks

Add paragraph breaks to flat ASR text (Gemma 270M)

Email Key-Line Bolding

Bold or highlight the key lines of an email (Gemma 270M)

Spoken Steganography

Encrypted message hidden in an AI podcast's sentence openers

My Benchmarks

Index of Daniel Rosehill's AI benchmarks and evals

Hebrew-in-Latin Token Classifier

Find romanized Hebrew words inside English text

My Weird Prompts — Dataset Navigator

Explore metadata of the My Weird Prompts datasets

Jerusalem Air Quality Shabbat Findings

Shabbat as a natural experiment for urban air quality

Geopol Forecast Council — Iran · Israel · US

Five-model LLM council forecasts Iran-Israel-US

Geopolitical Predictions

Predictive runs for a geopolitical analysis agenetic harness

Single Shot ASR Eval

Benchmarking 13 local STT models on AMD GPU with Handy

Audio Understanding Experiment

Testing Gemini 3.1's capabilities in audio understanding

Hebrew TTS Samples

Hebrew TTS provider comparison with voice cloning

The Agentic Symphony

Interactive map of agentic AI architecture