Daniel Rosehill PRO

danielrosehill

12 24 448

HongBenXian's profile picture

MIKI4005's profile picture

salman99669966's profile picture

https://www.danielrosehill.com

danielsrosehill
danielrosehill
danielrosehill
@danielrosehill.bsky.social‬

AI & ML interests

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

Recent Activity

published an article about 10 hours ago

Teaching TTS that *makolet* isn't English

updated a Space about 10 hours ago

danielrosehill/hebrew-latin-token-classifier

updated a collection about 10 hours ago

Parakeet V2 - English-Hebrew Codeswitching Finetune

View all activity

Organizations

danielrosehill 's collections 191

Parakeet V2 - English-Hebrew Codeswitching Finetune

Base fine tune and variants of Parakeet V2 English-Hebrew codeswitching finetune

danielrosehill/Parakeet-TDT-0.6B-v2-English-Hebrew-Codeswitching

Automatic Speech Recognition • 0.6B • Updated about 10 hours ago • 385
danielrosehill/Parakeet-TDT-0.6B-v2-English-Hebrew-Codeswitching-GGUF

Automatic Speech Recognition • 0.6B • Updated about 10 hours ago
danielrosehill/Parakeet-TDT-0.6B-v2-English-Hebrew-Codeswitching-ONNX

Automatic Speech Recognition • Updated about 10 hours ago
danielrosehill/Parakeet-TDT-0.6B-v2-English-Hebrew-Codeswitching-sherpa-onnx-int8

Automatic Speech Recognition • Updated about 10 hours ago

English-Hebrew Codeswitching - Models

Fine-tunes of ASR models on English-Hebrew codeswitching (English sentences with code-switching in Hebrew).

danielrosehill/Parakeet-TDT-0.6B-v2-English-Hebrew-Codeswitching

Automatic Speech Recognition • 0.6B • Updated about 10 hours ago • 385
danielrosehill/Whisper-Hebrish

0.8B • Updated Nov 18, 2025 • 21

My Models - Classifiers

danielrosehill/Voice-Note-Intent-Classifier

Text Classification • Updated 1 day ago
danielrosehill/hebrew-latin-token-classifier

Token Classification • 0.3B • Updated about 10 hours ago • 25

Fine Tune Candidates 1026

Candidates for a fine tuning idea for audio to text with deterministic post processing edits applied in one forward pass

nvidia/canary-1b

Automatic Speech Recognition • Updated Dec 3, 2025 • 2.9k • 463

Chatterbox Multilingual

Running on Zero

MCP

420

Chatterbox-Multilingual-TTS

🌎

420

Chatterbox TTS supporting 23 languages
mlx-community/chatterbox-multilingual-v3

Text-to-Speech • 0.7B • Updated Jul 31 • 5.03k • 7
mlx-community/S3TokenizerV2

0.1B • Updated Dec 5, 2025 • 6.98k

ASR Models 0926

A composite of models I've been trying and using across different devices in September 2026. Both ASR post-processing small models and multimodal.

oruk/orukeet

Automatic Speech Recognition • 0.6B • Updated 22 days ago • 42.4k • 101
pyannote/speaker-diarization-3.1

Automatic Speech Recognition • Updated May 10, 2024 • 6.84M • 4.42k
mlx-community/parakeet-tdt-0.6b-v3

Automatic Speech Recognition • 0.6B • Updated Aug 16, 2025 • 2.43M • 67
handy-computer/parakeet-unified-en-0.6b-gguf

Automatic Speech Recognition • 0.6B • Updated about 20 hours ago • 1.89M • 15

Small ASR Models

Small ASR models that aren't Whisper (or derivs). On device inference for smartphones etc

netease-youdao/Confucius4-R2T2

Automatic Speech Recognition • 2B • Updated 30 days ago • 48.5k • 578
oruk/orukeet

Automatic Speech Recognition • 0.6B • Updated 22 days ago • 42.4k • 101
nvidia/parakeet-tdt-0.6b-v3

Automatic Speech Recognition • 0.6B • Updated Aug 5 • 621k • • 1.2k
Qwen/Qwen3-ASR-1.7B

Automatic Speech Recognition • 2B • Updated Jan 30 • 1.13M • • 1.19k

Classifiers

Mapika/decider-2b

Text Classification • 2B • Updated 5 days ago • 334k • 107
danielrosehill/hebrew-latin-token-classifier

Token Classification • 0.3B • Updated about 10 hours ago • 25

Punctuation Restoration- English

st1992/bert-restore-punctuation

Token Classification • Updated Nov 20, 2021 • 10
superwhisper/s1-mini

Text Generation • 0.8B • Updated Aug 28 • 2.51k • 379
oliverguhr/fullstop-punctuation-multilang-large

Token Classification • 0.6B • Updated Nov 16, 2023 • 290k • • 182
superwhisper/s1-mini-GGUF

Text Generation • 0.8B • Updated Aug 28 • 265k • 44

Interesting Spaces

Running

23

Decision 2.0: Open Foundation Decision Models

⚡

23

One pass. Many decisions. Six Decision 2.0 models.

DeepSeek V4.1 Derivatives

dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8

Image-Text-to-Text • 763B • Updated Sep 11 • 57.2k • 683
drowzeys/DeepSeek-V4.1-Flash-Abliterated-Cybersecurity-Unleashed

Image-Text-to-Text • Updated Sep 14 • 202

Use Case Diversity

A collection intended as a first entry store for small models, especially component models, which perform modular tightly bounded tasks.

cua-ai/cua-s1-forms

Other • Updated 21 days ago • 116

Deepseek V4 Derivs

Community derivatives from Deepseek V4 and V4.1

dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8

Image-Text-to-Text • 763B • Updated Sep 11 • 57.2k • 683

STT Cleanup (Text Postprocessing)

Models that apply a text-to-text transformation as a second pass on speech transcribed using ASR.

sakusakumura/Qwen2-7b-cleanup

Text Generation • 8B • Updated Jun 10, 2024 • 105 • 1
sakusakumura/Qwen2-7b-cleanup-short-prompt

Text Generation • 8B • Updated Jun 10, 2024 • 108 • 1
superwhisper/s1-mini

Text Generation • 0.8B • Updated Aug 28 • 2.51k • 379
superwhisper/s1-mini-GGUF

Text Generation • 0.8B • Updated Aug 28 • 265k • 44

Israel Open Data

danielrosehill/Israel-Open-Data-Catalogue

Updated May 6 • 28
danielrosehill/Jerusalem-Air-Quality-Shabbat

Viewer • Updated Apr 28 • 7.95M • 140

Disfluency

4i-ai/BERT_disfluency_cls

Text Classification • 0.1B • Updated Aug 25, 2023 • 12 • 1
amaai-lab/DisfluencySpeech

Viewer • Updated Jun 27, 2024 • 5k • 428 • 22
shiprocket-ai/english-DisfluencySpeech

Viewer • Updated Feb 7 • 4.5k • 13
nyralabs/disfluency_speech_english

Viewer • Updated Jul 15 • 4.96k • 258 • 4

Hebrew Puncutation Restoration

verbit/hebrew_punctuation

Updated Oct 6, 2024 • 273 • 3

English Hebrew Translation

ashercn97/english-hebrew-translation

Translation • 77M • Updated Nov 12, 2023 • 28 • 2

Hebrew Diacritic Restoration Models

baravninaor/punctuation-restoration-deberta-alepgbert-hebrew

Updated Mar 22, 2023 • 1

Hebrew-TTS

Yzamari/f5tts-hebrew-v2

Text-to-Speech • 0.3B • Updated Mar 28 • 662 • 2
notmax123/Zonos-Hebrew

Text-to-Speech • Updated Sep 11, 2025 • 262 • 3

Utilities

Running

Featured

1.05k

Can You Run It? LLM version

🚀

1.05k

Check if your GPU can run a chosen LLM model

MWP-TTS-Candidates

ResembleAI/chatterbox-turbo

Text-to-Speech • Updated Dec 15, 2025 • • 698

ASR-To-Try

zai-org/GLM-ASR-Nano-2512

Automatic Speech Recognition • 2B • Updated Apr 7 • 55.4k • 388
nvidia/canary-qwen-2.5b

Automatic Speech Recognition • 3B • Updated Apr 21 • 46.3k • 470
microsoft/Phi-4-multimodal-instruct

Automatic Speech Recognition • 6B • Updated Dec 10, 2025 • 155k • 1.62k
facebook/omniASR-LLM-7B

Automatic Speech Recognition • Updated Nov 28, 2025 • 43

Evaluation Datasets

danielrosehill/Small-STT-Eval-Audio-Dataset

Viewer • Updated Dec 10, 2025 • 92 • 56

Voxtral Originals (Mistral)

The two official variants of Voxtral (audio multimodal model) released by Mistral in July 2025

mistralai/Voxtral-Mini-3B-2507

5B • Updated Jul 28, 2025 • 175k • 692
mistralai/Voxtral-Small-24B-2507

Audio-Text-to-Text • 24B • Updated Dec 20, 2025 • 22.4k • 541

Flux 2 Quants

city96/FLUX.2-dev-gguf

Image-to-Image • 32B • Updated Nov 29, 2025 • 82.1k • 167
gguf-org/flux2-dev-gguf

Image-to-Image • 18B • Updated Jan 1 • 8.86k • 65

My Public Audio Datasets

Open sourced audio datasets for STT/ASR. All recordings by me (Daniel Rosehill) unless otherwise accredited.

danielrosehill/English-Hebrew-Mixed-Sentences

Viewer • Updated 2 days ago • 637 • 101
danielrosehill/Tech-Sentences-For-ASR-Training

Viewer • Updated Nov 26, 2025 • 205 • 152 • 2
danielrosehill/Sample-Voice-Context-Data

Viewer • Updated Nov 30, 2025 • 159 • 19

TTS Models

Xenova/speecht5_tts

Text-to-Speech • Updated Aug 27, 2025 • 6.24k • 42
hexgrad/Kokoro-82M

Text-to-Speech • Updated Apr 10, 2025 • 10.4M • • 7.26k
microsoft/VibeVoice-1.5B

Text-to-Speech • 3B • Updated Jan 22 • 575k • 2.5k
neuphonic/neutts-air

Text-to-Speech • 0.7B • Updated Aug 26 • 1.83k • 906

ASR Resources

Useful datasets and models for ASR projects and fine tuning

ggerganov/whisper.cpp

Automatic Speech Recognition • Updated Oct 29, 2024 • 1.65k
openslr/librispeech_asr

Viewer • Updated Jul 25, 2025 • 585k • 63.3k • 249
speechcolab/gigaspeech

Viewer • Updated Feb 7 • 11.9M • 17.3k • 174
agentlans/high-quality-english-sentences

Viewer • Updated Oct 1, 2024 • 1.71M • 1.03k • 40

My-ASR-Finetunes

danielrosehill/Whisper-Hebrish

0.8B • Updated Nov 18, 2025 • 21
Running on Zero

Agents

Whisper Hebrish

🎤

Compare fine-tuned vs stock Whisper models

FUTO Models

futo-org/acft-whisper-tiny

Automatic Speech Recognition • 57.7M • Updated Jun 25, 2024 • 26 • 2
futo-org/acft-whisper-small.en

Automatic Speech Recognition • 0.3B • Updated Jun 25, 2024 • 13 • 2
futo-org/acft-whisper-base.en

Automatic Speech Recognition • 99.1M • Updated Jun 25, 2024 • 20 • 2
futo-org/acft-whisper-tiny.en

Automatic Speech Recognition • 57.7M • Updated Jun 25, 2024 • 19 • 1

ASR Benchmarking

Running on CPU Upgrade

Agents

Featured

1.5k

Open ASR Leaderboard

🏆

1.5k

Explore multilingual speech recognition model benchmarks
Sleeping

Agents

2

Asr Metrics

👀

2

Analyze ASR accuracy by comparing text files
danielrosehill/Podcast-ASR-Evaluation

Viewer • Updated Nov 14, 2025 • 27 • 23

API Price Comparisons

Running

1

Agentic LLM Price Comparisons

🤖

1

218 tool-calling LLMs analyzed by cost and context
danielrosehill/Open-Router-API-Pricing-Analysis

Viewer • Updated Nov 10, 2025 • 2.38k • 143

My LORAS

danielrosehill/Jerusalem-Images

Text-to-Image • Updated Nov 6, 2025 • 14 •
danielrosehill/Tel-Aviv-Street-Style

Text-to-Image • Updated Nov 6, 2025 • 7 •
danielrosehill/Herman-Poppleberry

Text-to-Image • Updated Nov 6, 2025 • 7 •
danielrosehill/Dinosaur-Sloth

Text-to-Image • Updated Nov 6, 2025 • 13 •

To Check Out

MiniMaxAI/MiniMax-M2

Text Generation • 229B • Updated Dec 23, 2025 • 195k • • 1.51k
stabilityai/sp4d

Updated Nov 5, 2025 • 125 • 15
Falconsai/text_summarization

Summarization • 60.5M • Updated Feb 17, 2024 • 19.8k • • 326
distil-whisper/distil-large-v3

Automatic Speech Recognition • 0.8B • Updated Apr 21 • 592k • 384

Architecture Related Models

Collection of models gathered together for my wife who is an architect (of buildings!)

Muapi/jj-s-architecture-office-building

Text-to-Image • Updated May 13 • 8 •
prithivMLmods/Canopus-Interior-Architecture-0.1

Text-to-Image • Updated Aug 4, 2024 • 147 • • 27

Image to 3D

Running on Zero

MCP

764

TRELLIS

🏢

764

Scalable and Versatile 3D Generation from images

My Ideas

Running

2

Claude Agent Picker Pattern

🎯

2

Pattern for managing multi-agent crews in Claude Code

Whisper Base + variants

openai/whisper-base

Automatic Speech Recognition • 72.6M • Updated Feb 29, 2024 • 1.62M • 306
openai/whisper-base.en

Automatic Speech Recognition • 72.6M • Updated Jan 22, 2024 • 151k • 58
onnx-community/whisper-base_timestamped

Automatic Speech Recognition • Updated Mar 5, 2025 • 33.2k • 32
Systran/faster-whisper-base

Automatic Speech Recognition • Updated Nov 23, 2023 • 1.61M • 46

Voice Modality Apps

Runtime error

Agents

2

Voice Generated Visions

🦀

2

Cloud-Native Voice to-Image Generation using LLMs and GenAI

Worlds (3D, Games)

Running on Zero

Agents

196

HunyuanWorld-Mirror

🌍

196

Universal 3D World Reconstruction with Any Prior Prompting

Demos

Runtime error

Agents

Baby Noise Cancellation Demo

👶

AI-powered baby noise removal demo with STT comparison
Running

Nano Banana Sketch Cleanup

🎨

AI sketch cleanup with before/after comparisons

Background Noise Removal

Runtime error

Agents

Baby Noise Cancellation Demo

👶

AI-powered baby noise removal demo with STT comparison
Running

Agents

186

DeepFilterNet2

💩

186

Denoise your recordings and view spectrograms
Running

Agents

20

DeepFilterNet2 No File Size Limit

😻

20

Use DeepFilterNet2 to denoise audio no file size limit

Vibe Coding

Running

Gemini Vibe Coded POCs

🚀

Explore AI tools for productivity, creativity, analysis, and utilities

Project Indexes

Running

AI Project Index

🏆

Navigable index of AI projects, tools, and agents
Running

Gemini Vibe Coded POCs

🚀

Explore AI tools for productivity, creativity, analysis, and utilities

AI UIs

Sleeping

Agents

Pen Pal AI

📮

Write letters and get thoughtful AI replies

Voice Enhancement

Running

Agents

20

BroadcastAudioUpscaling

🌖

20

Enhance broadcast audio quality with super‑resolution upscaling
Running on Zero

Agents

64

Apollo

💻

64

Restore and enhance audio files with AI models

Taxonomies

Sleeping

Agents

Multimodal AI Taxonomy

🌍
danielrosehill/multimodal-ai-taxonomy

Viewer • Updated Oct 22, 2025 • 85 • 76

Veo 3.1

Running

Agents

601

veo3.1-fast

🐨

601

Generate videos from text prompts or images

Architecture

benlehrburger/modern-architecture

Viewer • Updated May 31, 2023 • 1.09k • 590 • 4
Sleeping

Agents

2

ArchitectureClassifier

📈

2

Classify architectural styles in images
Running

Agents

17

Rocco Architecture Render

🚀

17

Generate interior and exterior designs from sketches
Sleeping

Agents

1

London Architecture

💻

1

Classify architectural styles in images

Style Transfer

Running

367

SD Artists Browser

🤘

367

Explore artist styles and build SDXL prompts
Running on Zero

MCP

65

StyleAligned Transfer

🐠

65

Generate images in the style of a reference image
Paused

Agents

17

StyleFeatureEditor

💻

17

Edit images with predefined styles or text prompts
Runtime error

Agents

12

Kontext Style LoRAs

🌍

12

Transform images using selected styles

Geolocation Utilities

Running on Zero

Agents

11

Location Predictor

🌍

11

Predict the location of any photo and view it on a map

Image Generation

Running on Zero

Agents

314

Sketch2lineart

🚀

314

Generate high‑quality lineart from your image

Security Tools

Running

Agents

28

GLiNER-Multi-PII

💻

28

Extract personally identifiable information from text

Developer Utilities

Running on Zero

Agents

Featured

932

Screenshot to HTML

⚡

932

Generate HTML code from a website screenshot

Medical

Running

3

Pharmacology Graph Explorer

💊

3

Explore predicted drug‑target and disease links
Running

Agents

76

Medical Diagnosis

📉

76

Classify symptoms to diagnose health issues
Running

29

MediAI Medical AI Agent

🚀

29

AI-Powered Diagnosis & Treatment Assistant
Sleeping

Agents

Lisdexamfetamine Split Dose Modeller

🚀

Model split-dose protocols for lisdexamfetamine/Vyvanse

CAD Utilities

Running on CPU Upgrade

Agents

Featured

138

SGS 1

🚀

138

Generate 3D CAD models from images

Subtitle generation

Sleeping

Agents

12

Whisper WebUI

🚀

12

Generate subtitles from audio or video files

Game creation

Running

Featured

256

3D Game Maker

🏢

256

create games with AI

OSINT

Spaces and models that may have applications in open source intelligence (OSINT)

Running

157

Reverse Face Search

📉

157

Search Face Online
Runtime error

Agents

SATINT Analyst

👁

Professional satellite imagery intelligence analysis
Running on Zero

Agents

11

Location Predictor

🌍

11

Predict the location of any photo and view it on a map

Interesting ideas

AI use-cases and appliations that I found interesting (a repo for myself to explore!)

Running on Zero

Agents

Featured

2.32k

MagicQuill

🪶

2.32k

Edit images with sketches, colors, and text prompts
Build error

Agents

20

AutoPR

🚀

20

Generate a Twitter or Xiaohongshu post from a research PDF
Running

157

Reverse Face Search

📉

157

Search Face Online
Runtime error

Agents

16

AI STORYTELLER

🏢

16

Generate a video from a story

Background Removal

Running on Zero

MCP

2.97k

Background Removal

🌘

2.97k

Remove backgrounds from images instantly
Running on Zero

Agents

Featured

656

Video Background Removal

📽

656

Remove/Change background of video.
Running on Zero

Agents

974

BRIA RMBG 2.0

🐢

974

remove background from any image

Image captioning

Salesforce/blip-image-captioning-base

Image-to-Text • Updated Feb 3, 2025 • 1.32M • 900

Video Generation Quants

QuantStack/Wan2.2-I2V-A14B-GGUF

Image-to-Video • 14B • Updated Jul 29, 2025 • 608k • 443

OCR & Document Processing

dots-studio/dots.ocr

Image-Text-to-Text • 3B • Updated Oct 31, 2025 • 762k • 1.34k
Runtime error

15

Ui Rev Doc Model

😻

15

Analysis of data on an invoice
Paused

Agents

Featured

145

Deepdoctection

🏃

145

Convert PDFs and images to structured text and layout data
Running

13

Docsifer

📚

13

Convert documents into clean, LLM-ready Markdown.

Fast video generation

lightx2v/Wan2.2-Lightning

Text-to-Video • Updated Nov 13, 2025 • 91 • 637
ByteDance/AnimateDiff-Lightning

Text-to-Video • Updated Jan 6, 2025 • 25.3k • 1.01k

Agentic code generation capable

Qwen/Qwen3-Coder-30B-A3B-Instruct

Text Generation • 31B • Updated Dec 3, 2025 • 439k • • 1.29k

256K Context

Qwen/Qwen3-Coder-30B-A3B-Instruct

Text Generation • 31B • Updated Dec 3, 2025 • 439k • • 1.29k

Video Generation

chetwinlow1/Ovi

Image-to-Video • 12B • Updated Nov 15, 2025 • 71 • • 302
lightx2v/Wan2.2-Lightning

Text-to-Video • Updated Nov 13, 2025 • 91 • 637
Wan-AI/Wan2.2-T2V-A14B

Text-to-Video • Updated Aug 7, 2025 • 4.74k • • 577
QuantStack/Wan2.2-I2V-A14B-GGUF

Image-to-Video • 14B • Updated Jul 29, 2025 • 608k • 443

Reasoning Models

ai21labs/AI21-Jamba-Reasoning-3B

Text Generation • 3B • Updated Oct 8, 2025 • 41k • 140
IFM/K2-Think

Text Generation • 33B • Updated Nov 19, 2025 • 231 • • 369
unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF

Text Generation • 8B • Updated Jun 16, 2025 • 109k • 466

Instructional LLMs

LLMs optimised for instruction following rather than conversational use - quants and original models

meta-llama/Llama-3.1-8B-Instruct

Text Generation • 8B • Updated Sep 25, 2024 • 5.76M • • 8.46k
Qwen/Qwen3-Omni-30B-A3B-Instruct

Any-to-Any • 35B • Updated Sep 22, 2025 • 721k • 1.03k
moonshotai/Kimi-K2-Instruct-0905

Text Generation • 1T • Updated Jan 30 • 53.2k • • 790
mistralai/Mistral-7B-Instruct-v0.3

7B • Updated Dec 3, 2025 • 1.99M • 3.8k

Deep research

FractalAIResearch/Fathom-Search-4B

Text Generation • 4B • Updated Oct 10, 2025 • 74 • • 122
Running

Agents

26

Fathom DeepResearch

📊

26

DeepResearch with the fathom search and synthesizer models

Mobile LLMs

LLMs optimised for running "on-device" (specifically, for this collection, on smartphones with standard inference capabilities)

facebook/MobileLLM-Pro

Text Generation • 1B • Updated Nov 11, 2025 • 8 • 164

Agentic LLMs

zai-org/GLM-4.6

Text Generation • 357B • Updated Sep 30, 2025 • 19.3k • • 1.24k
AgentFlow/agentflow-planner-7b

8B • Updated Oct 12, 2025 • 542 • 64
HuggingFaceH4/zephyr-7b-beta

Text Generation • 7B • Updated Oct 16, 2024 • 91.3k • • 1.86k
zai-org/GLM-4.5-Air

Text Generation • 110B • Updated Aug 11, 2025 • 725k • • 646

Local model collection

LLMs (mostly quants) that are small enough to run locally (on my hardware). My go-tos.

Qwen/Qwen3-VL-8B-Instruct

Image-Text-to-Text • 9B • Updated Oct 15, 2025 • 6.56M • • 1.21k
zai-org/GLM-4.6

Text Generation • 357B • Updated Sep 30, 2025 • 19.3k • • 1.24k
Qwen/Qwen3-VL-8B-Thinking

Image-Text-to-Text • 9B • Updated Nov 26, 2025 • 107k • • 229
meta-llama/Llama-3.1-8B-Instruct

Text Generation • 8B • Updated Sep 25, 2024 • 5.76M • • 8.46k

My Image Datasets

danielrosehill/Hebrew-Language-Signage

Viewer • Updated Nov 6, 2025 • 68 • 62
danielrosehill/Jerusalem-Streetscapes

Viewer • Updated Nov 6, 2025 • 413 • 33
danielrosehill/Tel-Aviv-Pics

Updated Nov 6, 2025 • 42
danielrosehill/Jerusalem-High-Rise-Development

Viewer • Updated Nov 6, 2025 • 56 • 76

Datasets

danielrosehill/Zapier-Integrations-260825

Viewer • Updated Aug 26, 2025 • 8.64k • 19

Text Transformation

danielrosehill/Shakespearean-Text-Transformation-Prompts

Viewer • Updated Apr 21, 2025 • 1 • 28
danielrosehill/Speech-To-Text-System-Prompts-2

Viewer • Updated Apr 9, 2025 • 2 • 82 • 2
Sleeping

Agents

System Prompt Reformatter

📚

Reformats system prompts in the 2nd person and other edits
Sleeping

Agents

BLUF Email Formatter

📧

Format emails with clear subject lines and summaries

Evaluations

danielrosehill/ChatGPT-AI-Vs-API

Updated Apr 22, 2025 • 2
danielrosehill/Long-Prompt-Experiment

Viewer • Updated Aug 19, 2025 • 92 • 82
danielrosehill/STT-Voice-Notes-Evals

Updated Aug 11, 2025 • 194

Jerusalem

danielrosehill/Jerusalem-Emergency-Shelters-0925

Viewer • Updated Sep 19, 2025 • 149 • 17
danielrosehill/Jerusalem-Streetscapes

Viewer • Updated Nov 6, 2025 • 413 • 33
danielrosehill/Jerusalem-High-Rise-Development

Viewer • Updated Nov 6, 2025 • 56 • 76

ISO Standards

ISO standard related projects

danielrosehill/ISO-3166-4217-Consolidated

Preview • Updated Sep 3, 2025 • 12

Sustainability Projects

Datasets and projects related to sustainability esp impact investing

danielrosehill/GHG-Emissions-Data

Viewer • Updated Dec 20, 2024 • 78 • 189
danielrosehill/Global-Value-Factor-Database-Refactor-V2

Updated Sep 2, 2025 • 261
danielrosehill/ifvi_valuefactors_deriv

Updated Aug 21, 2025 • 263
danielrosehill/pay-for-outcomes-instruments

Preview • Updated May 21, 2025 • 11

Character Creation Datasets

Datasets for generating characters from 2D/3D

danielrosehill/Corn-The-Sloth

Viewer • Updated Apr 18, 2025 • 109 • 20

Israel Photo Galleries

Photo galleries of places in Israel for world generation use cases, among others

danielrosehill/Tel-Aviv-Pics

Updated Nov 6, 2025 • 42
danielrosehill/Jerusalem-High-Rise-Development

Viewer • Updated Nov 6, 2025 • 56 • 76

3D-General

Running on Zero

Agents

Featured

2.3k

Hunyuan3D-2.1

👻

2.3k

Image-to-3D Generation
Running on Zero

MCP

764

TRELLIS

🏢

764

Scalable and Versatile 3D Generation from images
Running on Zero

Agents

3.41k

Hunyuan3D-2.0

🌍

3.41k

Text-to-3D and Image-to-3D Generation

QR Art

Running on Zero

Agents

Featured

2k

QR Code AI Art Generator

📱

2k

QR Code AI Art Generator Blend QR codes with AI Art

Single Shot Image To Image (Reference)

Running on Zero

Agents

Featured

1.96k

PhotoMaker

📷

1.96k

Generate personalized photos of a person from a prompt

Text To Speech (TTS)

Runtime error

Agents

Featured

2.76k

XTTS

🐸

2.76k

Generate speech from text using a reference voice
microsoft/VibeVoice-1.5B

Text-to-Speech • 3B • Updated Jan 22 • 575k • 2.5k
hexgrad/Kokoro-82M

Text-to-Speech • Updated Apr 10, 2025 • 10.4M • • 7.26k

Music Generation

Running on Zero

Agents

Featured

5.11k

MusicGen

🎵

5.11k

Generate music from a text description and optional melody
suno/bark

Text-to-Speech • Updated Oct 4, 2023 • 25k • 1.58k
Running on L40S

Featured

753

Song Prep

🎵

753

Transcribe song lyrics with timestamps

Character-Generation

Running on Zero

Agents

196

PSHuman

🏃

196

PHOTOREALISTIC HUMAN RECONSTRUCTION w/ CROSS-SCALE DIFF
Runtime error

MCP

11

3D Game Environment Builder

📚

11

3D Game Environment Builder MCP

AI Experiments

Experiments in AI and prompt engineering

Sleeping

Max Output Tokens Analysis

📊

Display max output tokens for models over time
Sleeping

Agents

1

LLM Long Output Experiment (Code Generation)

📈

1

Evaluating max single output length of code gen LLMs
Running

Single Shot Brevity Training

📈

Using one example to train an LLM for informational brevity
Sleeping

Agents

Local STT Eval One Sample

😻

Single sample eval for WER on various Whisper models

Useful-Models

modularai/Llama-3.1-8B-Instruct-GGUF

Text Generation • 8B • Updated Sep 9, 2024 • 7.28k • 17
MaziyarPanahi/WizardLM-2-7B-GGUF

Text Generation • 7B • Updated Apr 15, 2024 • 98k • 83
MaziyarPanahi/mathstral-7B-v0.1-GGUF

Text Generation • 7B • Updated Jul 16, 2024 • 97.1k • 8
MaziyarPanahi/phi-4-GGUF

Text Generation • 15B • Updated Jan 8, 2025 • 108k • 10

Hebrew datasets

Datasets in Hebrew

imvladikon/hebrew_speech_coursera

Viewer • Updated May 5, 2023 • 21k • 421 • 10
imvladikon/hebrew_speech_kan

Viewer • Updated May 5, 2023 • 10k • 493 • 15
sivan22/hebrew-handwritten-dataset

Viewer • Updated May 8, 2023 • 5.09k • 44 • 16
imvladikon/hebrew_speech_campus

Viewer • Updated Nov 20, 2023 • 75.9k • 300 • 7

ASR Models

Collection of ASR models for customized STT model training

nvidia/parakeet-tdt-0.6b-v2

Automatic Speech Recognition • Updated Jun 29 • 194k • 1.56k
ibm-granite/granite-speech-3.3-8b

Automatic Speech Recognition • 9B • Updated Apr 2 • 13.1k • 171
nvidia/canary-qwen-2.5b

Automatic Speech Recognition • 3B • Updated Apr 21 • 46.3k • 470
facebook/omniASR-W2V-1B

Automatic Speech Recognition • Updated Nov 27, 2025 • 6

Fav-Code-Generation-Models

Qwen/Qwen2.5-Coder-32B-Instruct

Text Generation • 33B • Updated Jan 12, 2025 • 723k • • 2.18k
deepseek-ai/DeepSeek-V2.5-1210

Text Generation • 236B • Updated Dec 11, 2024 • 2.5k • 271

LLM-Experiments

Sleeping

Agents

1

LLM Long Output Experiment (Code Generation)

📈

1

Evaluating max single output length of code gen LLMs
GiliGold/Knesset-DictaBERT

Fill-Mask • 0.2B • Updated Dec 28, 2024 • 59 • 2

English Hebrew Codeswitching - Datasets And Training

Datasets and training materials for English-Hebrew codeswitching ASR and multimodal (audio+text to text) models

danielrosehill/English-Hebrew-Codeswitching-Sentences

Updated about 14 hours ago • 200
danielrosehill/Read-Aloud-Voice-Sentences

Viewer • Updated about 13 hours ago • 1.9k • 298
danielrosehill/English-Hebrew-Mixed-Sentences

Viewer • Updated 2 days ago • 637 • 101

Inventory Accessories

danielrosehill/inventory-spec-extractor

Token Classification • Updated 1 day ago
danielrosehill/inventory-spec-lines

Viewer • Updated 1 day ago • 14.4k • 49

Code Switching (English And Hebrew) - All Resources

Datasets and fine tunes (mine) focused on English (primary) with Hebrew code-switching. Targeted use-case: improved ASR accuracy among olim

danielrosehill/Parakeet-TDT-0.6B-v2-English-Hebrew-Codeswitching

Automatic Speech Recognition • 0.6B • Updated about 10 hours ago • 385
danielrosehill/English-Hebrew-Codeswitching-Sentences

Updated about 14 hours ago • 200
danielrosehill/Whisper-Hebrish

0.8B • Updated Nov 18, 2025 • 21
danielrosehill/Read-Aloud-Voice-Sentences

Viewer • Updated about 13 hours ago • 1.9k • 298

Baby Cry Detection

AmeerHesham/distilhubert-finetuned-baby_cry

Audio Classification • 23.7M • Updated May 7 • 159 • 2

Token classifiers

Token classification models. Use-case: Linguistic identification for code switching in TTS script normalization.

fastino/gliner2.5-multi-v1

0.3B • Updated 8 days ago • 202k • 279

Pidgeon Detection NVR

A few models to try in Frigate for presence detection of pigeons.

OpenVINO/ssd_mobilenet_v2-int8-ov

Object Detection • Updated Jul 2 • 28
hustvl/yolos-tiny

Object Detection • 6.49M • Updated Apr 10, 2024 • 78.9k • 282
birder-project/mobilenet_v4_l_eu-common

Image Classification • Updated Mar 4, 2025 • 25

Small Text Generation

meta-llama/Llama-3.2-1B-Instruct

Text Generation • 1B • Updated Oct 24, 2024 • 5.84M • • 1.85k
Qwen/Qwen3-0.6B

Text Generation • 0.8B • Updated Jul 26, 2025 • 29.9M • • 1.82k
empero-ai/Qwen3.8-2B-Distill-GGUF

Text Generation • 2B • Updated Aug 16 • 484k • 166

IVM And Text Restoration

superwhisper/s1-mini

Text Generation • 0.8B • Updated Aug 28 • 2.51k • 379
superwhisper/s1-mini-GGUF

Text Generation • 0.8B • Updated Aug 28 • 265k • 44
Folx/qwen3-0.6b-pl-text-normalization

Text Generation • 0.6B • Updated May 9 • 487 • 3
DD0101/disfluency-large

Token Classification • Updated Apr 9, 2023 • 11

Encoders

google/electra-base-discriminator

Updated Feb 29, 2024 • 41.9M • 217

On-Device ASR - One Plus CPH2493 (Nord 3)

Models used for on device speech to text with the OnePlus CPH2493.

nvidia/parakeet-tdt-1.1b

Automatic Speech Recognition • Updated Dec 3, 2025 • 2.23k • 141
nvidia/parakeet-tdt-0.6b-v3

Automatic Speech Recognition • 0.6B • Updated Aug 5 • 621k • • 1.2k
nvidia/nemotron-3.5-asr-streaming-0.6b

Automatic Speech Recognition • 0.6B • Updated Sep 10 • 1.21M • • 1.21k
handy-computer/parakeet-tdt-1.1b-gguf

Automatic Speech Recognition • 1B • Updated about 20 hours ago • 25.3k • 1

On Device Models

Cactus-Compute/needle3

Text Generation • Updated 6 days ago • 160k • 337

Decision Making Support

keras-io/TF_Decision_Trees

Tabular Classification • Updated Jul 5, 2024 • 93 • 7
convaiinnovations/laya

Text Classification • 0.4B • Updated 13 days ago • 49.8k • • 5.66k
DoccyHealth/Solomon

Text Classification • Updated 26 days ago • 53
vllm-sr/Decision-1.0-Nox-4B

Zero-Shot Classification • Updated 6 days ago • 577 • 17

Deepseek V4.1

deepseek-ai/DeepSeek-V4.1-Flash

Image-Text-to-Text • 763B • Updated about 19 hours ago • 1.28M • • 4.57k
dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8

Image-Text-to-Text • 763B • Updated Sep 11 • 57.2k • 683

Android STT - Favorites

Speech to text models that I've had the best experience with on my current hardware (One Plus Nord 3 ). Currently this is mostly ASR models.

nvidia/parakeet-tdt-0.6b-v3

Automatic Speech Recognition • 0.6B • Updated Aug 5 • 621k • • 1.2k
nvidia/parakeet-tdt-1.1b

Automatic Speech Recognition • Updated Dec 3, 2025 • 2.23k • 141
nvidia/nemotron-3.5-asr-streaming-0.6b

Automatic Speech Recognition • 0.6B • Updated Sep 10 • 1.21M • • 1.21k

Acronym Identification

Kamakshi88/t5_acronym

0.2B • Updated Feb 1, 2024 • 5

LLMS-Im-Testing

google/gemma-4-E4B

Any-to-Any • 8B • Updated Jul 15 • 610k • 466

Hebrew Sentiment Classification Models

DGurgurov/xlm-r_hebrew_sentiment

Text Classification • 0.3B • Updated Jun 8, 2024 • 18

Hebrew OCR Models

sivan22/testing-trOCR-hebrew-handwritten

Image-Text-to-Text • Updated May 17, 2023 • 74 • 1

Hebrew ASR

imvladikon/wav2vec2-large-xlsr-53-hebrew

Automatic Speech Recognition • 0.3B • Updated May 6, 2023 • 17.7k • 8
Mizurodp/wav2vec2-large-xls-r-300m-hebrew-colab

Automatic Speech Recognition • Updated Dec 17, 2022 • 36 • 1
imvladikon/wav2vec2-xls-r-300m-lm-hebrew

Automatic Speech Recognition • 0.3B • Updated Sep 15, 2023 • 68 • 4
imvladikon/wav2vec2-xls-r-1b-hebrew

Automatic Speech Recognition • 1.0B • Updated Sep 12, 2023 • 747 • 2

Streaming-Speech-To-Text

nvidia/nemotron-speech-streaming-en-0.6b

Automatic Speech Recognition • 0.6B • Updated Aug 5 • 181k • 640
mistralai/Voxtral-Mini-4B-Realtime-2602

Automatic Speech Recognition • 4B • Updated Mar 11 • 2.04M • 1.03k

Agentic Code Gen 301225

Quick collection of models I'm evaluating for cogeneration. Minimum inclusion criteria includes tool usage and MCP. Looking for something fast and goo

zai-org/GLM-4.7

Text Generation • 358B • Updated Jan 29 • 84.7k • • 2.07k
MiniMaxAI/MiniMax-M2.1

Text Generation • 229B • Updated Feb 13 • 10.3k • • 1.37k
XiaomiMiMo/MiMo-V2-Flash

Text Generation • 310B • Updated Jul 9 • 74.3k • • 755
unsloth/MiniMax-M2.1-GGUF

Text Generation • 229B • Updated Feb 14 • 3.85k • 195

Video Understanding

lmms-lab/LLaVA-Video-7B-Qwen2

Video-Text-to-Text • 8B • Updated Oct 25, 2024 • 11k • 127

Image Evaluations

danielrosehill/Hebrew-Image-Eval-111225

Updated Dec 11, 2025 • 291

Audio Understanding Datasets

nvidia/AF-Think

Preview • Updated Apr 5 • 724 • 27
nvidia/AudioSkills

Preview • Updated Jan 8 • 1.49k • 109
nvidia/LongAudio

Preview • Updated Apr 5 • 321 • 26

Audio Multimodal Models

Open source models with audio understanding. Tracking mostly vendor releases in the audio and text to text subclassification of multimodal.

stepfun-ai/Step-Audio-R1

Audio-Text-to-Text • 33B • Updated Dec 2, 2025 • 16 • 144
Qwen/Qwen2-Audio-7B

Audio-Text-to-Text • 8B • Updated Nov 20, 2024 • 24.8k • 181
Qwen/Qwen2-Audio-7B-Instruct

Audio-Text-to-Text • 8B • Updated Jan 12, 2025 • 232k • 570
FreedomIntelligence/Soundwave

Audio-Text-to-Text • 9B • Updated Mar 16, 2025 • 112 • 15

My Whisper ACFT Fine Tunes

Whisper fine tunes for use with FUTO keyboard on Android (training: Modal based on Whisper-ACFT skeleton from FUTO)

danielrosehill/daniel_whisper_acft_base_v2

99.1M • Updated Nov 25, 2025 • 7
danielrosehill/daniel_whisper_acft_small_v2

0.3B • Updated Nov 25, 2025 • 16
danielrosehill/daniel_whisper_acft_tiny_v2

57.7M • Updated Nov 25, 2025 • 14

My Whisper Fine-Tunes (V2)

Whisper fine-tunes for my voice and vocab (tech, Hebrew). About 1 hour of training data so still very much POCs!

danielrosehill/daniel_whisper_finetune_large_v3_turbo_v2

Automatic Speech Recognition • 0.8B • Updated Nov 23, 2025 • 18
danielrosehill/daniel_whisper_finetune_medium_v2

Automatic Speech Recognition • 0.8B • Updated Nov 23, 2025 • 10
danielrosehill/daniel_whisper_finetune_tiny_v2

Automatic Speech Recognition • 37.8M • Updated Nov 23, 2025 • 8
danielrosehill/daniel_whisper_finetune_base_v2

Automatic Speech Recognition • 72.6M • Updated Nov 23, 2025 • 7

ASR Beyond Whisper

nvidia/parakeet-tdt-0.6b-v3

Automatic Speech Recognition • 0.6B • Updated Aug 5 • 621k • • 1.2k
ibm-granite/granite-speech-3.3-8b

Automatic Speech Recognition • 9B • Updated Apr 2 • 13.1k • 171
facebook/seamless-m4t-v2-large

Automatic Speech Recognition • 2B • Updated Jan 4, 2024 • 301k • 1.03k
facebook/wav2vec2-base-960h

Automatic Speech Recognition • 94.4M • Updated Nov 14, 2022 • 1.75M • 410

Whisper Hebrish

Fine tune of Whisper Large (V3, Turbo) using a small corpus of mixed language English sentences with Hebrew to improve accuracy

Running on Zero

Agents

Whisper Hebrish

🎤

Compare fine-tuned vs stock Whisper models
danielrosehill/Whisper-Hebrish

0.8B • Updated Nov 18, 2025 • 21
danielrosehill/English-Hebrew-Mixed-Sentences

Viewer • Updated 2 days ago • 637 • 101

Old LLMs

Useful models for demonstrating what early and pre-Transformer LLMs looked and functioned like

TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF

1B • Updated Dec 31, 2023 • 79.1k • 237

My-Evaluations

danielrosehill/Podcast-ASR-Evaluation

Viewer • Updated Nov 14, 2025 • 27 • 23
danielrosehill/Long-Prompt-Experiment

Viewer • Updated Aug 19, 2025 • 92 • 82
Sleeping

Agents

Podcast ASR Evaluation

🎙

ASR benchmark comparing local and cloud models
Sleeping

Agents

1

LLM Long Output Experiment (Code Generation)

📈

1

Evaluating max single output length of code gen LLMs

Whisper Fine Tunes

Whisper fine-tuned on 1 hour of my voice

Running

Whisper Fine-Tune vs Commercial APIs

🎤

Local fine-tunes beat commercial STT APIs

PDF Downloads

Running

4.08k

The Ultra-Scale Playbook

🌌

4.08k

The ultimate guide to training LLM on large GPU Clusters

STT Components

Models that work in unison with core STT models in voice workflows

pyannote/voice-activity-detection

Automatic Speech Recognition • Updated May 10, 2024 • 473k • 243
pyannote/speaker-diarization-3.1

Automatic Speech Recognition • Updated May 10, 2024 • 6.84M • 4.42k
pyannote/overlapped-speech-detection

Automatic Speech Recognition • Updated May 10, 2024 • 1.83k • 65
pipecat-ai/smart-turn-v3

Voice Activity Detection • Updated Jan 7 • 212

Video background removal

Running on Zero

Agents

Featured

367

Remove Video Background

🎞

367

Easily remove your videos background!

STT Fine Tune Resources

unsloth/whisper-large-v3

Automatic Speech Recognition • 2B • Updated May 14, 2025 • 3.71k • 20
unsloth/whisper-small

Automatic Speech Recognition • 0.2B • Updated May 14, 2025 • 1.25k • 7
unsloth/CrisperWhisper

Automatic Speech Recognition • 2B • Updated May 14, 2025 • 287 • 17
unsloth/whisper-large-v3-turbo

Automatic Speech Recognition • 0.8B • Updated May 14, 2025 • 4.2k • 13

Concept Outlines

Running

2

Claude Agent Picker Pattern

🎯

2

Pattern for managing multi-agent crews in Claude Code

STT Evaluations

Sleeping

Agents

Local STT Eval One Sample

😻

Single sample eval for WER on various Whisper models
danielrosehill/Podcast-ASR-Evaluation

Viewer • Updated Nov 14, 2025 • 27 • 23
Sleeping

Agents

Podcast ASR Evaluation

🎙

ASR benchmark comparing local and cloud models
Running

STT Comparison

🦀

Comparing STT models against audio

Whisper variants

nyralabs/CrisperWhisper

Automatic Speech Recognition • 2B • Updated Jul 22 • 16.5k • 345

Entertainment Recommendations

Running

Agents

10

MovieReccomender

📚

10

Get a personalized recommendation using AI

Proofs of Concept

Runtime error

Agents

Baby Noise Cancellation Demo

👶

AI-powered baby noise removal demo with STT comparison

Deep Filter

Running

Agents

20

DeepFilterNet2 No File Size Limit

😻

20

Use DeepFilterNet2 to denoise audio no file size limit

Gemini

Running

Gemini Vibe Coded POCs

🚀

Explore AI tools for productivity, creativity, analysis, and utilities

Claude Code

Sleeping

Agents

Claude Code Slash Commands

⚡

Interactive browser for Claude Code slash commands
Running

1

Claude Code Linux Desktop Slash Commands

🖥

1

Slashes for Linux Desktop admin

Shakespeare AI

Just for fun projects for converting conventional text into Shakespearean English

Paused

Agents

Featured

30

Diffusion GPT

🖊

30

Generate Shakespearean text using a diffusion model
Runtime error

Shakespeare AI

😻

Rewrites .. stuff .. in Shakespearean English

Real Time Video To Video

Running on CPU Upgrade

Featured

105

Krea Realtime Video

👁

105

Generate AI videos from webcam, video, or text
krea/krea-realtime-video

Text-to-Video • 14B • Updated Sep 8 • 4.3k • 309

Multimodal AI

Sleeping

Agents

Multimodal AI Taxonomy

🌍
danielrosehill/multimodal-ai-taxonomy

Viewer • Updated Oct 22, 2025 • 85 • 76
Running

Gemini Vibe Coded POCs

🚀

Explore AI tools for productivity, creativity, analysis, and utilities

Context Utilities

Experimentary workflows (mostly) that aim to rethink how contextual data can be gathered to achieve personalised inference in AI systems

Sleeping

2

AI Context Generation Interviews

⚡

2

Model workflow using agents to proactively develop context
Sleeping

Agents

Context Cruncher

🎙

Transform voice recordings into structured AI context data

Avatar Videos

Running on Zero

MCP

Featured

628

LatentSync

👄

628

Audio Conditioned LipSync with Latent Diffusion Models
Build error

Agents

Featured

1.43k

SadTalker

😭

1.43k

Generate a talking face video from an image and audio
Running

Agents

194

Gradio Lipsync Wav2lip

👄

194

Generate lip‑synced video from a face image and audio
Running

Agents

71

Wav2lip Gpu

🌍

71

Create a talking‑head video from a photo and audio

Resume Utilities

Runtime error

2

ATS Resume Checker

🌖

2

Parse resumes and match with job descriptions
Sleeping

Agents

2

Resume Matcher

🚀

2

Match resume with job description

Multi LLM Experiments

Running on CPU Upgrade

60

Outsmart

🧠

60

Watch LLMs negotiate in a real‑time battle arena

Leaderboards

Running

22

AudioBench Leaderboard

🥇

22

View AudioBench leaderboard and compare model scores
Running

121

AI Phone Leaderboard

📱

121

AI Phone Leaderboard
Running

Agents

363

VBench Leaderboard

📊

363

Submit video model evaluation results to a public benchmark

Object Detection

Running

Agents

Featured

101

Yolov10

📉

101

Detect objects in images with customizable YOLOv10 models

Text Processing Utilities

Running

Agents

28

GLiNER-Multi-PII

💻

28

Extract personally identifiable information from text
Sleeping

4

MarkItDown Microsoft

🐠

4

Extract Text in Structured Format

Data Visualization

Running

3

neulab/conala

🗺

3

Display interactive data visualizations

Hugging Face Utilities

Sleeping

Agents

8

HF Downloader

📈

8

Download Hugging Face repositories to run locally.✔

Scraping

Running

MCP

117

Web Scraper

🚀

117

Scrape a website and download its content as markdown

Video editing utilities

Runtime error

Agents

31

LaMa Video Watermark Remover

🌖

31

Remove watermarks from videos
Sleeping

Agents

9

AudioDenoiser

👁

9

Remove background noise from videos
Paused

11

Image Video Colorization

🎥

11

Colorize black and white videos into full color

Audio editing utilities

Running

Agents

467

Remove Silence From Audio

🦀

467

Remove Silence From Audio
Running on Zero

Agents

415

Audio🔹Separator

🏃

415

Vocal and background audio separator
Running on Zero

Agents

Featured

330

Audio Editing

🎧

330

Edit audios with text prompts
Running on Zero

Agents

481

Resemble Enhance

🚀

481

Enhance your audio with denoising and quality boost

Prompt engineering

Running

151

Prompt Lab

😻

151

Enhance your prompt into a structured, expert‑level version

Data Processing Utilities

Running on Zero

Agents

679

MinerU Document Extraction Tools

📚

679

Embedded MinerU document extraction demo
Running

MCP

117

Web Scraper

🚀

117

Scrape a website and download its content as markdown
Running

Agents

105

PDF to Dataset

📄

105

Convert PDFs to a Hugging Face dataset

Image To Video

Running on Zero

MCP

Featured

1.61k

LTX Video Fast

🎥

1.61k

ultra-fast video model, LTX 0.9.8 13B distilled

Video To Video

QuantStack/Wan2.2-Animate-14B-GGUF

Video-to-Video • 17B • Updated Sep 20, 2025 • 252k • 231

TTS With Dialog Support

nari-labs/Dia-1.6B

Text-to-Speech • 2B • Updated Jun 1, 2025 • 22.2k • • 2.93k

Diarisation

pyannote/speaker-diarization-community-1

Automatic Speech Recognition • Updated Sep 29, 2025 • 5.39M • 3.02k

Long speech synthesis

microsoft/VibeVoice-1.5B

Text-to-Speech • 3B • Updated Jan 22 • 575k • 2.5k

Browser use capable

Qwen/Qwen3-Coder-30B-A3B-Instruct

Text Generation • 31B • Updated Dec 3, 2025 • 439k • • 1.29k

Code Generation Models

Qwen/Qwen3-Coder-30B-A3B-Instruct

Text Generation • 31B • Updated Dec 3, 2025 • 439k • • 1.29k

General LLM Quants

ai21labs/AI21-Jamba-Mini-1.7

52B • Updated Feb 2 • 287 • 44

Embedding Models

google/embeddinggemma-300m

Sentence Similarity • 0.3B • Updated Sep 25, 2025 • 3.03M • • 2.03k
nvidia/omni-embed-nemotron-3b

Sentence Similarity • 5B • Updated May 6 • 3.67k • 132
Qwen/Qwen3-Embedding-0.6B

Feature Extraction • 0.6B • Updated Apr 20 • 8.59M • • 1.29k
google/embeddinggemma-2

Feature Extraction • 0.7B • Updated 11 days ago • 151k • 2.52k

Image Generation Models

tencent/HunyuanImage-3.0

Text-to-Image • 83B • Updated Jan 28 • 1.58k • • 1.15k
black-forest-labs/FLUX.1-schnell

Text-to-Image • 12B • Updated Aug 16, 2024 • 563k • • 6.3k
stabilityai/stable-diffusion-xl-base-1.0

Text-to-Image • 3B • Updated Oct 30, 2023 • 4.25M • • 8.35k
Qwen/Qwen-Image

Text-to-Image • 20B • Updated Aug 18, 2025 • 277k • • 2.67k

Image Generation Quants

Quantized versions of image generation models

lightx2v/Qwen-Image-Lightning

Text-to-Image • Updated Nov 3, 2025 • 259k • • 840

LLMs

zai-org/GLM-4.6

Text Generation • 357B • Updated Sep 30, 2025 • 19.3k • • 1.24k

Voice Cloning

neuphonic/neutts-air

Text-to-Speech • 0.7B • Updated Aug 26 • 1.83k • 906
coqui/XTTS-v2

Text-to-Speech • Updated Dec 11, 2023 • 6.19M • 3.89k
Running on Zero

Agents

102

Voice Cloning Studio

🚀

102

This space offers an easy-to-use interface for voice cloning

Vision Language Models

Qwen/Qwen3-VL-8B-Instruct

Image-Text-to-Text • 9B • Updated Oct 15, 2025 • 6.56M • • 1.21k
moondream/moondream3-preview

Image-Text-to-Text • 9B • Updated Apr 9 • 92.5k • 691

Audio Datasets

danielrosehill/ai-generated-podcast-episodes

Viewer • Updated Aug 26, 2025 • 66 • 58 • 1
danielrosehill/Small-STT-Eval-Audio-Dataset

Viewer • Updated Dec 10, 2025 • 92 • 56
danielrosehill/Read-Aloud-Voice-Sentences

Viewer • Updated about 13 hours ago • 1.9k • 298
danielrosehill/English-Hebrew-Codeswitching-Sentences

Updated about 14 hours ago • 200

Context Data

danielrosehill/Software-Wish-List-Context-Data

Updated Apr 28, 2025 • 21

Experiments

danielrosehill/Long-Prompt-Experiment

Viewer • Updated Aug 19, 2025 • 92 • 82
Runtime error

Agents

AI Agent UN - Multi-Agent Simulation Framework

🏛

Explore UN voting simulations with AI agents
Sleeping

Max Output Tokens Analysis

📊

Display max output tokens for models over time

AI Agents

AI agent network configs and projects

danielrosehill/Code-Gen-Agents-0925

Updated Sep 15, 2025 • 22
Runtime error

Agents

AI Agent UN - Multi-Agent Simulation Framework

🏛

Explore UN voting simulations with AI agents
Sleeping

Agents

Code Gen Agents Network

🔥

Code generation agent network with config navigator

Israel

Projects related to Israel

danielrosehill/Israel-Alerting-Zones

Preview • Updated May 9, 2025 • 28
danielrosehill/Tel-Aviv-Pics

Updated Nov 6, 2025 • 42
danielrosehill/Jerusalem-Streetscapes

Viewer • Updated Nov 6, 2025 • 413 • 33
danielrosehill/Jerusalem-Emergency-Shelters-0925

Viewer • Updated Sep 19, 2025 • 149 • 17

Reference / Lookup Datasets

danielrosehill/ISO-3166-4217-Consolidated

Preview • Updated Sep 3, 2025 • 12

Voice Note Audio And Training

Datasets for STT training, classification fine-tuning - especially voice notes

danielrosehill/Voice-Note-Audio

Preview • Updated Oct 27, 2025 • 128

My System Prompt Collections

Collections of system prompts for assistants, agents, and workflows

danielrosehill/Data-Utils-System-Prompts

Updated Apr 9, 2025 • 48
danielrosehill/Email-Management-System-Prompts

Updated Apr 9, 2025 • 10
danielrosehill/General-Purpose-System-Prompts

Updated Apr 9, 2025 • 22 • 1
danielrosehill/Geopolitical-System-Prompts

Updated Apr 9, 2025 • 18

3D Human Digital Humans

Running on Zero

Agents

196

PSHuman

🏃

196

PHOTOREALISTIC HUMAN RECONSTRUCTION w/ CROSS-SCALE DIFF
Runtime error

Agents

11

Pifuhd

🐠

11

Generate 3D human models from images
Running on Zero

Agents

10

HumanWild

⚡

10

Generate 3D human reconstructions from images
Runtime error

51

HSMR

💀

51

Convert images of humans to biomechanically accurate 3D skeletons

Image To Image

Running on Zero

Agents

Featured

1.67k

Expression Editor

🐨

1.67k

Quickly edit the expression of a face
Running on Zero

Agents

Featured

1.54k

InstructPix2Pix

🚀

1.54k

Edit images using text instructions
Qwen/Qwen-Image-Edit-2509

Image-to-Image • 20B • Updated Sep 22, 2025 • 465k • • 1.26k
Qwen/Qwen-Image

Text-to-Image • 20B • Updated Aug 18, 2025 • 277k • • 2.67k

Upscalers

Running on Zero

Agents

2.19k

Finegrain Image Enhancer

🖼

2.19k

Clarity AI Upscaler Reproduction
Running on Zero

Agents

183

RealESRGAN Pytorch

🔥

183

User Friendly Image & Video Upscaler!

Speech To Text (STT)

Running on Zero

Agents

Featured

2.87k

Whisper

📉

2.87k

Transcribe audio or YouTube video into text
openai/whisper-large-v3

Automatic Speech Recognition • 2B • Updated Aug 12, 2024 • 3.72M • • 6.66k
ggerganov/whisper.cpp

Automatic Speech Recognition • Updated Oct 29, 2024 • 1.65k

Image To Video (No Audio)

Running on Zero

Agents

3.81k

Live Portrait

🤪

3.81k

Apply the motion of a video on a portrait
Running on Zero

MCP

Featured

2.04k

Stable Video Diffusion 1.1

📺

2.04k

Generate a short video from a single image
Running on Zero

MCP

Featured

1.62k

Wan2.1 Fast

🎥

1.62k

Animate an image into a short video using a text prompt

Image Editing Utilities

Running on Zero

MCP

2.97k

Background Removal

🌘

2.97k

Remove backgrounds from images instantly
Running on Zero

Agents

2.98k

CLIP Interrogator

🕵

2.98k

Generate detailed prompts from any image
Paused

Agents

441

NoWatermark

⚡

441

Powerful Watermark Removal API
Running

Agents

142

Vectorizer AI

🌍

142

Convert images to SVG vectors with customizable settings

Global Value Factor Database (GVFD) - Visualisation And Data

Version controlled refactors for data analysis of the Global Value Factor Database (GVFD) by the International Foundation for Valuing Impacts (IFVI).

Sleeping

Agents

GVFD Navigator

📉

Data visualisation utility for GVFD by IFVI (unofficial)
danielrosehill/Global-Value-Factor-Database-Refactor-V2

Updated Sep 2, 2025 • 261
danielrosehill/ifvi_valuefactors_deriv

Updated Aug 21, 2025 • 263

Text Reformatting Apps

Implementations of apps for simple text reformatting tasks

Sleeping

Agents

BLUF Email Formatter

📧

Format emails with clear subject lines and summaries
Runtime error

Agents

System Prompt Depersonaliser

😻

Converts personal system prompts for general use
Runtime error

Shakespeare AI

😻

Rewrites .. stuff .. in Shakespearean English

Hebrew AI Spaces

Spaces to do with Hebrew language AI

Running on CPU Upgrade

Agents

46

Hebrew LLM Leaderboard

🥇

46

Explore LLM benchmark leaderboard with searchable filters
Sleeping

Agents

Hebrew GPT Neo - Science Fiction and Fantasy

🧙

Generate Hebrew text for science fiction and fantasy stories
Running

Agents

מחולל נונסנס רובושאול

🤖

מחולל משפטים בסגנון ״חיות כיס״
Build error

Agents

Hebrew Sentiment

😻

Benchmarks

Running on CPU Upgrade

Agents

Featured

1.5k

Open ASR Leaderboard

🏆

1.5k

Explore multilingual speech recognition model benchmarks
Running

Agents

34

Hebrew Transcription Leaderboard

🥇

34

Benchmarking Hebrew Speech-to-Text Models
Running

Agents

453

Agent Leaderboard

💬

453

Ranking of LLMs for agentic tasks

Vintage-LLMs

openai-community/gpt2

Text Generation • 0.1B • Updated Feb 19, 2024 • 16.2M • 4.26k

Hebrew Large Language Models

Language models supporting TTS (predominantly the text generation task). These are almost exclusively fine-tunes of Gemma, Mistral, or the Qwen models

GiliGold/Knesset-DictaBERT

Fill-Mask • 0.2B • Updated Dec 28, 2024 • 59 • 2
yam-peleg/Hebrew-Gemma-11B

Text Generation • 10B • Updated Mar 16, 2024 • 105 • 38
yam-peleg/Hebrew-Mistral-7B

Text Generation • 8B • Updated Apr 26, 2024 • 443 • 73
yam-peleg/Hebrew-Mistral-7B-200K

Text Generation • 8B • Updated May 6, 2024 • 55 • 15

Parakeet V2 - English-Hebrew Codeswitching Finetune

Base fine tune and variants of Parakeet V2 English-Hebrew codeswitching finetune

danielrosehill/Parakeet-TDT-0.6B-v2-English-Hebrew-Codeswitching

Automatic Speech Recognition • 0.6B • Updated about 10 hours ago • 385
danielrosehill/Parakeet-TDT-0.6B-v2-English-Hebrew-Codeswitching-GGUF

Automatic Speech Recognition • 0.6B • Updated about 10 hours ago
danielrosehill/Parakeet-TDT-0.6B-v2-English-Hebrew-Codeswitching-ONNX

Automatic Speech Recognition • Updated about 10 hours ago
danielrosehill/Parakeet-TDT-0.6B-v2-English-Hebrew-Codeswitching-sherpa-onnx-int8

Automatic Speech Recognition • Updated about 10 hours ago

English Hebrew Codeswitching - Datasets And Training

Datasets and training materials for English-Hebrew codeswitching ASR and multimodal (audio+text to text) models

danielrosehill/English-Hebrew-Codeswitching-Sentences

Updated about 14 hours ago • 200
danielrosehill/Read-Aloud-Voice-Sentences

Viewer • Updated about 13 hours ago • 1.9k • 298
danielrosehill/English-Hebrew-Mixed-Sentences

Viewer • Updated 2 days ago • 637 • 101

English-Hebrew Codeswitching - Models

Fine-tunes of ASR models on English-Hebrew codeswitching (English sentences with code-switching in Hebrew).

danielrosehill/Parakeet-TDT-0.6B-v2-English-Hebrew-Codeswitching

Automatic Speech Recognition • 0.6B • Updated about 10 hours ago • 385
danielrosehill/Whisper-Hebrish

0.8B • Updated Nov 18, 2025 • 21

Inventory Accessories

danielrosehill/inventory-spec-extractor

Token Classification • Updated 1 day ago
danielrosehill/inventory-spec-lines

Viewer • Updated 1 day ago • 14.4k • 49

My Models - Classifiers

danielrosehill/Voice-Note-Intent-Classifier

Text Classification • Updated 1 day ago
danielrosehill/hebrew-latin-token-classifier

Token Classification • 0.3B • Updated about 10 hours ago • 25

Code Switching (English And Hebrew) - All Resources

Datasets and fine tunes (mine) focused on English (primary) with Hebrew code-switching. Targeted use-case: improved ASR accuracy among olim

danielrosehill/Parakeet-TDT-0.6B-v2-English-Hebrew-Codeswitching

Automatic Speech Recognition • 0.6B • Updated about 10 hours ago • 385
danielrosehill/English-Hebrew-Codeswitching-Sentences

Updated about 14 hours ago • 200
danielrosehill/Whisper-Hebrish

0.8B • Updated Nov 18, 2025 • 21
danielrosehill/Read-Aloud-Voice-Sentences

Viewer • Updated about 13 hours ago • 1.9k • 298

Fine Tune Candidates 1026

Candidates for a fine tuning idea for audio to text with deterministic post processing edits applied in one forward pass

nvidia/canary-1b

Automatic Speech Recognition • Updated Dec 3, 2025 • 2.9k • 463

Baby Cry Detection

AmeerHesham/distilhubert-finetuned-baby_cry

Audio Classification • 23.7M • Updated May 7 • 159 • 2

Chatterbox Multilingual

Running on Zero

MCP

420

Chatterbox-Multilingual-TTS

🌎

420

Chatterbox TTS supporting 23 languages
mlx-community/chatterbox-multilingual-v3

Text-to-Speech • 0.7B • Updated Jul 31 • 5.03k • 7
mlx-community/S3TokenizerV2

0.1B • Updated Dec 5, 2025 • 6.98k

Token classifiers

Token classification models. Use-case: Linguistic identification for code switching in TTS script normalization.

fastino/gliner2.5-multi-v1

0.3B • Updated 8 days ago • 202k • 279

ASR Models 0926

A composite of models I've been trying and using across different devices in September 2026. Both ASR post-processing small models and multimodal.

oruk/orukeet

Automatic Speech Recognition • 0.6B • Updated 22 days ago • 42.4k • 101
pyannote/speaker-diarization-3.1

Automatic Speech Recognition • Updated May 10, 2024 • 6.84M • 4.42k
mlx-community/parakeet-tdt-0.6b-v3

Automatic Speech Recognition • 0.6B • Updated Aug 16, 2025 • 2.43M • 67
handy-computer/parakeet-unified-en-0.6b-gguf

Automatic Speech Recognition • 0.6B • Updated about 20 hours ago • 1.89M • 15

Pidgeon Detection NVR

A few models to try in Frigate for presence detection of pigeons.

OpenVINO/ssd_mobilenet_v2-int8-ov

Object Detection • Updated Jul 2 • 28
hustvl/yolos-tiny

Object Detection • 6.49M • Updated Apr 10, 2024 • 78.9k • 282
birder-project/mobilenet_v4_l_eu-common

Image Classification • Updated Mar 4, 2025 • 25

Small ASR Models

Small ASR models that aren't Whisper (or derivs). On device inference for smartphones etc

netease-youdao/Confucius4-R2T2

Automatic Speech Recognition • 2B • Updated 30 days ago • 48.5k • 578
oruk/orukeet

Automatic Speech Recognition • 0.6B • Updated 22 days ago • 42.4k • 101
nvidia/parakeet-tdt-0.6b-v3

Automatic Speech Recognition • 0.6B • Updated Aug 5 • 621k • • 1.2k
Qwen/Qwen3-ASR-1.7B

Automatic Speech Recognition • 2B • Updated Jan 30 • 1.13M • • 1.19k

Small Text Generation

meta-llama/Llama-3.2-1B-Instruct

Text Generation • 1B • Updated Oct 24, 2024 • 5.84M • • 1.85k
Qwen/Qwen3-0.6B

Text Generation • 0.8B • Updated Jul 26, 2025 • 29.9M • • 1.82k
empero-ai/Qwen3.8-2B-Distill-GGUF

Text Generation • 2B • Updated Aug 16 • 484k • 166

Classifiers

Mapika/decider-2b

Text Classification • 2B • Updated 5 days ago • 334k • 107
danielrosehill/hebrew-latin-token-classifier

Token Classification • 0.3B • Updated about 10 hours ago • 25

IVM And Text Restoration

superwhisper/s1-mini

Text Generation • 0.8B • Updated Aug 28 • 2.51k • 379
superwhisper/s1-mini-GGUF

Text Generation • 0.8B • Updated Aug 28 • 265k • 44
Folx/qwen3-0.6b-pl-text-normalization

Text Generation • 0.6B • Updated May 9 • 487 • 3
DD0101/disfluency-large

Token Classification • Updated Apr 9, 2023 • 11

Punctuation Restoration- English

st1992/bert-restore-punctuation

Token Classification • Updated Nov 20, 2021 • 10
superwhisper/s1-mini

Text Generation • 0.8B • Updated Aug 28 • 2.51k • 379
oliverguhr/fullstop-punctuation-multilang-large

Token Classification • 0.6B • Updated Nov 16, 2023 • 290k • • 182
superwhisper/s1-mini-GGUF

Text Generation • 0.8B • Updated Aug 28 • 265k • 44

Encoders

google/electra-base-discriminator

Updated Feb 29, 2024 • 41.9M • 217

Interesting Spaces

Running

23

Decision 2.0: Open Foundation Decision Models

⚡

23

One pass. Many decisions. Six Decision 2.0 models.

On-Device ASR - One Plus CPH2493 (Nord 3)

Models used for on device speech to text with the OnePlus CPH2493.

nvidia/parakeet-tdt-1.1b

Automatic Speech Recognition • Updated Dec 3, 2025 • 2.23k • 141
nvidia/parakeet-tdt-0.6b-v3

Automatic Speech Recognition • 0.6B • Updated Aug 5 • 621k • • 1.2k
nvidia/nemotron-3.5-asr-streaming-0.6b

Automatic Speech Recognition • 0.6B • Updated Sep 10 • 1.21M • • 1.21k
handy-computer/parakeet-tdt-1.1b-gguf

Automatic Speech Recognition • 1B • Updated about 20 hours ago • 25.3k • 1

DeepSeek V4.1 Derivatives

dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8

Image-Text-to-Text • 763B • Updated Sep 11 • 57.2k • 683
drowzeys/DeepSeek-V4.1-Flash-Abliterated-Cybersecurity-Unleashed

Image-Text-to-Text • Updated Sep 14 • 202

On Device Models

Cactus-Compute/needle3

Text Generation • Updated 6 days ago • 160k • 337

Use Case Diversity

A collection intended as a first entry store for small models, especially component models, which perform modular tightly bounded tasks.

cua-ai/cua-s1-forms

Other • Updated 21 days ago • 116

Decision Making Support

keras-io/TF_Decision_Trees

Tabular Classification • Updated Jul 5, 2024 • 93 • 7
convaiinnovations/laya

Text Classification • 0.4B • Updated 13 days ago • 49.8k • • 5.66k
DoccyHealth/Solomon

Text Classification • Updated 26 days ago • 53
vllm-sr/Decision-1.0-Nox-4B

Zero-Shot Classification • Updated 6 days ago • 577 • 17

Deepseek V4 Derivs

Community derivatives from Deepseek V4 and V4.1

dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8

Image-Text-to-Text • 763B • Updated Sep 11 • 57.2k • 683

Deepseek V4.1

deepseek-ai/DeepSeek-V4.1-Flash

Image-Text-to-Text • 763B • Updated about 19 hours ago • 1.28M • • 4.57k
dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8

Image-Text-to-Text • 763B • Updated Sep 11 • 57.2k • 683

STT Cleanup (Text Postprocessing)

Models that apply a text-to-text transformation as a second pass on speech transcribed using ASR.

sakusakumura/Qwen2-7b-cleanup

Text Generation • 8B • Updated Jun 10, 2024 • 105 • 1
sakusakumura/Qwen2-7b-cleanup-short-prompt

Text Generation • 8B • Updated Jun 10, 2024 • 108 • 1
superwhisper/s1-mini

Text Generation • 0.8B • Updated Aug 28 • 2.51k • 379
superwhisper/s1-mini-GGUF

Text Generation • 0.8B • Updated Aug 28 • 265k • 44

Android STT - Favorites

Speech to text models that I've had the best experience with on my current hardware (One Plus Nord 3 ). Currently this is mostly ASR models.

nvidia/parakeet-tdt-0.6b-v3

Automatic Speech Recognition • 0.6B • Updated Aug 5 • 621k • • 1.2k
nvidia/parakeet-tdt-1.1b

Automatic Speech Recognition • Updated Dec 3, 2025 • 2.23k • 141
nvidia/nemotron-3.5-asr-streaming-0.6b

Automatic Speech Recognition • 0.6B • Updated Sep 10 • 1.21M • • 1.21k

Israel Open Data

danielrosehill/Israel-Open-Data-Catalogue

Updated May 6 • 28
danielrosehill/Jerusalem-Air-Quality-Shabbat

Viewer • Updated Apr 28 • 7.95M • 140

Acronym Identification

Kamakshi88/t5_acronym

0.2B • Updated Feb 1, 2024 • 5

Disfluency

4i-ai/BERT_disfluency_cls

Text Classification • 0.1B • Updated Aug 25, 2023 • 12 • 1
amaai-lab/DisfluencySpeech

Viewer • Updated Jun 27, 2024 • 5k • 428 • 22
shiprocket-ai/english-DisfluencySpeech

Viewer • Updated Feb 7 • 4.5k • 13
nyralabs/disfluency_speech_english

Viewer • Updated Jul 15 • 4.96k • 258 • 4

LLMS-Im-Testing

google/gemma-4-E4B

Any-to-Any • 8B • Updated Jul 15 • 610k • 466

Hebrew Puncutation Restoration

verbit/hebrew_punctuation

Updated Oct 6, 2024 • 273 • 3

Hebrew Sentiment Classification Models

DGurgurov/xlm-r_hebrew_sentiment

Text Classification • 0.3B • Updated Jun 8, 2024 • 18

English Hebrew Translation

ashercn97/english-hebrew-translation

Translation • 77M • Updated Nov 12, 2023 • 28 • 2

Hebrew OCR Models

sivan22/testing-trOCR-hebrew-handwritten

Image-Text-to-Text • Updated May 17, 2023 • 74 • 1

Hebrew Diacritic Restoration Models

baravninaor/punctuation-restoration-deberta-alepgbert-hebrew

Updated Mar 22, 2023 • 1

Hebrew ASR

imvladikon/wav2vec2-large-xlsr-53-hebrew

Automatic Speech Recognition • 0.3B • Updated May 6, 2023 • 17.7k • 8
Mizurodp/wav2vec2-large-xls-r-300m-hebrew-colab

Automatic Speech Recognition • Updated Dec 17, 2022 • 36 • 1
imvladikon/wav2vec2-xls-r-300m-lm-hebrew

Automatic Speech Recognition • 0.3B • Updated Sep 15, 2023 • 68 • 4
imvladikon/wav2vec2-xls-r-1b-hebrew

Automatic Speech Recognition • 1.0B • Updated Sep 12, 2023 • 747 • 2

Hebrew-TTS

Yzamari/f5tts-hebrew-v2

Text-to-Speech • 0.3B • Updated Mar 28 • 662 • 2
notmax123/Zonos-Hebrew

Text-to-Speech • Updated Sep 11, 2025 • 262 • 3

Streaming-Speech-To-Text

nvidia/nemotron-speech-streaming-en-0.6b

Automatic Speech Recognition • 0.6B • Updated Aug 5 • 181k • 640
mistralai/Voxtral-Mini-4B-Realtime-2602

Automatic Speech Recognition • 4B • Updated Mar 11 • 2.04M • 1.03k

Utilities

Running

Featured

1.05k

Can You Run It? LLM version

🚀

1.05k

Check if your GPU can run a chosen LLM model

Agentic Code Gen 301225

Quick collection of models I'm evaluating for cogeneration. Minimum inclusion criteria includes tool usage and MCP. Looking for something fast and goo

zai-org/GLM-4.7

Text Generation • 358B • Updated Jan 29 • 84.7k • • 2.07k
MiniMaxAI/MiniMax-M2.1

Text Generation • 229B • Updated Feb 13 • 10.3k • • 1.37k
XiaomiMiMo/MiMo-V2-Flash

Text Generation • 310B • Updated Jul 9 • 74.3k • • 755
unsloth/MiniMax-M2.1-GGUF

Text Generation • 229B • Updated Feb 14 • 3.85k • 195

MWP-TTS-Candidates

ResembleAI/chatterbox-turbo

Text-to-Speech • Updated Dec 15, 2025 • • 698

Video Understanding

lmms-lab/LLaVA-Video-7B-Qwen2

Video-Text-to-Text • 8B • Updated Oct 25, 2024 • 11k • 127

ASR-To-Try

zai-org/GLM-ASR-Nano-2512

Automatic Speech Recognition • 2B • Updated Apr 7 • 55.4k • 388
nvidia/canary-qwen-2.5b

Automatic Speech Recognition • 3B • Updated Apr 21 • 46.3k • 470
microsoft/Phi-4-multimodal-instruct

Automatic Speech Recognition • 6B • Updated Dec 10, 2025 • 155k • 1.62k
facebook/omniASR-LLM-7B

Automatic Speech Recognition • Updated Nov 28, 2025 • 43

Image Evaluations

danielrosehill/Hebrew-Image-Eval-111225

Updated Dec 11, 2025 • 291

Evaluation Datasets

danielrosehill/Small-STT-Eval-Audio-Dataset

Viewer • Updated Dec 10, 2025 • 92 • 56

Audio Understanding Datasets

nvidia/AF-Think

Preview • Updated Apr 5 • 724 • 27
nvidia/AudioSkills

Preview • Updated Jan 8 • 1.49k • 109
nvidia/LongAudio

Preview • Updated Apr 5 • 321 • 26

Voxtral Originals (Mistral)

The two official variants of Voxtral (audio multimodal model) released by Mistral in July 2025

mistralai/Voxtral-Mini-3B-2507

5B • Updated Jul 28, 2025 • 175k • 692
mistralai/Voxtral-Small-24B-2507

Audio-Text-to-Text • 24B • Updated Dec 20, 2025 • 22.4k • 541

Audio Multimodal Models

Open source models with audio understanding. Tracking mostly vendor releases in the audio and text to text subclassification of multimodal.

stepfun-ai/Step-Audio-R1

Audio-Text-to-Text • 33B • Updated Dec 2, 2025 • 16 • 144
Qwen/Qwen2-Audio-7B

Audio-Text-to-Text • 8B • Updated Nov 20, 2024 • 24.8k • 181
Qwen/Qwen2-Audio-7B-Instruct

Audio-Text-to-Text • 8B • Updated Jan 12, 2025 • 232k • 570
FreedomIntelligence/Soundwave

Audio-Text-to-Text • 9B • Updated Mar 16, 2025 • 112 • 15

Flux 2 Quants

city96/FLUX.2-dev-gguf

Image-to-Image • 32B • Updated Nov 29, 2025 • 82.1k • 167
gguf-org/flux2-dev-gguf

Image-to-Image • 18B • Updated Jan 1 • 8.86k • 65

My Whisper ACFT Fine Tunes

Whisper fine tunes for use with FUTO keyboard on Android (training: Modal based on Whisper-ACFT skeleton from FUTO)

danielrosehill/daniel_whisper_acft_base_v2

99.1M • Updated Nov 25, 2025 • 7
danielrosehill/daniel_whisper_acft_small_v2

0.3B • Updated Nov 25, 2025 • 16
danielrosehill/daniel_whisper_acft_tiny_v2

57.7M • Updated Nov 25, 2025 • 14

My Public Audio Datasets

Open sourced audio datasets for STT/ASR. All recordings by me (Daniel Rosehill) unless otherwise accredited.

danielrosehill/English-Hebrew-Mixed-Sentences

Viewer • Updated 2 days ago • 637 • 101
danielrosehill/Tech-Sentences-For-ASR-Training

Viewer • Updated Nov 26, 2025 • 205 • 152 • 2
danielrosehill/Sample-Voice-Context-Data

Viewer • Updated Nov 30, 2025 • 159 • 19

My Whisper Fine-Tunes (V2)

Whisper fine-tunes for my voice and vocab (tech, Hebrew). About 1 hour of training data so still very much POCs!

danielrosehill/daniel_whisper_finetune_large_v3_turbo_v2

Automatic Speech Recognition • 0.8B • Updated Nov 23, 2025 • 18
danielrosehill/daniel_whisper_finetune_medium_v2

Automatic Speech Recognition • 0.8B • Updated Nov 23, 2025 • 10
danielrosehill/daniel_whisper_finetune_tiny_v2

Automatic Speech Recognition • 37.8M • Updated Nov 23, 2025 • 8
danielrosehill/daniel_whisper_finetune_base_v2

Automatic Speech Recognition • 72.6M • Updated Nov 23, 2025 • 7

TTS Models

Xenova/speecht5_tts

Text-to-Speech • Updated Aug 27, 2025 • 6.24k • 42
hexgrad/Kokoro-82M

Text-to-Speech • Updated Apr 10, 2025 • 10.4M • • 7.26k
microsoft/VibeVoice-1.5B

Text-to-Speech • 3B • Updated Jan 22 • 575k • 2.5k
neuphonic/neutts-air

Text-to-Speech • 0.7B • Updated Aug 26 • 1.83k • 906

ASR Beyond Whisper

nvidia/parakeet-tdt-0.6b-v3

Automatic Speech Recognition • 0.6B • Updated Aug 5 • 621k • • 1.2k
ibm-granite/granite-speech-3.3-8b

Automatic Speech Recognition • 9B • Updated Apr 2 • 13.1k • 171
facebook/seamless-m4t-v2-large

Automatic Speech Recognition • 2B • Updated Jan 4, 2024 • 301k • 1.03k
facebook/wav2vec2-base-960h

Automatic Speech Recognition • 94.4M • Updated Nov 14, 2022 • 1.75M • 410

ASR Resources

Useful datasets and models for ASR projects and fine tuning

ggerganov/whisper.cpp

Automatic Speech Recognition • Updated Oct 29, 2024 • 1.65k
openslr/librispeech_asr

Viewer • Updated Jul 25, 2025 • 585k • 63.3k • 249
speechcolab/gigaspeech

Viewer • Updated Feb 7 • 11.9M • 17.3k • 174
agentlans/high-quality-english-sentences

Viewer • Updated Oct 1, 2024 • 1.71M • 1.03k • 40

Whisper Hebrish

Fine tune of Whisper Large (V3, Turbo) using a small corpus of mixed language English sentences with Hebrew to improve accuracy

Running on Zero

Agents

Whisper Hebrish

🎤

Compare fine-tuned vs stock Whisper models
danielrosehill/Whisper-Hebrish

0.8B • Updated Nov 18, 2025 • 21
danielrosehill/English-Hebrew-Mixed-Sentences

Viewer • Updated 2 days ago • 637 • 101

My-ASR-Finetunes

danielrosehill/Whisper-Hebrish

0.8B • Updated Nov 18, 2025 • 21
Running on Zero

Agents

Whisper Hebrish

🎤

Compare fine-tuned vs stock Whisper models

Old LLMs

Useful models for demonstrating what early and pre-Transformer LLMs looked and functioned like

TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF

1B • Updated Dec 31, 2023 • 79.1k • 237

FUTO Models

futo-org/acft-whisper-tiny

Automatic Speech Recognition • 57.7M • Updated Jun 25, 2024 • 26 • 2
futo-org/acft-whisper-small.en

Automatic Speech Recognition • 0.3B • Updated Jun 25, 2024 • 13 • 2
futo-org/acft-whisper-base.en

Automatic Speech Recognition • 99.1M • Updated Jun 25, 2024 • 20 • 2
futo-org/acft-whisper-tiny.en

Automatic Speech Recognition • 57.7M • Updated Jun 25, 2024 • 19 • 1

My-Evaluations

danielrosehill/Podcast-ASR-Evaluation

Viewer • Updated Nov 14, 2025 • 27 • 23
danielrosehill/Long-Prompt-Experiment

Viewer • Updated Aug 19, 2025 • 92 • 82
Sleeping

Agents

Podcast ASR Evaluation

🎙

ASR benchmark comparing local and cloud models
Sleeping

Agents

1

LLM Long Output Experiment (Code Generation)

📈

1

Evaluating max single output length of code gen LLMs

ASR Benchmarking

Running on CPU Upgrade

Agents

Featured

1.5k

Open ASR Leaderboard

🏆

1.5k

Explore multilingual speech recognition model benchmarks
Sleeping

Agents

2

Asr Metrics

👀

2

Analyze ASR accuracy by comparing text files
danielrosehill/Podcast-ASR-Evaluation

Viewer • Updated Nov 14, 2025 • 27 • 23

Whisper Fine Tunes

Whisper fine-tuned on 1 hour of my voice

Running

Whisper Fine-Tune vs Commercial APIs

🎤

Local fine-tunes beat commercial STT APIs

API Price Comparisons

Running

1

Agentic LLM Price Comparisons

🤖

1

218 tool-calling LLMs analyzed by cost and context
danielrosehill/Open-Router-API-Pricing-Analysis

Viewer • Updated Nov 10, 2025 • 2.38k • 143

PDF Downloads

Running

4.08k

The Ultra-Scale Playbook

🌌

4.08k

The ultimate guide to training LLM on large GPU Clusters

My LORAS

danielrosehill/Jerusalem-Images

Text-to-Image • Updated Nov 6, 2025 • 14 •
danielrosehill/Tel-Aviv-Street-Style

Text-to-Image • Updated Nov 6, 2025 • 7 •
danielrosehill/Herman-Poppleberry

Text-to-Image • Updated Nov 6, 2025 • 7 •
danielrosehill/Dinosaur-Sloth

Text-to-Image • Updated Nov 6, 2025 • 13 •

STT Components

Models that work in unison with core STT models in voice workflows

pyannote/voice-activity-detection

Automatic Speech Recognition • Updated May 10, 2024 • 473k • 243
pyannote/speaker-diarization-3.1

Automatic Speech Recognition • Updated May 10, 2024 • 6.84M • 4.42k
pyannote/overlapped-speech-detection

Automatic Speech Recognition • Updated May 10, 2024 • 1.83k • 65
pipecat-ai/smart-turn-v3

Voice Activity Detection • Updated Jan 7 • 212

To Check Out

MiniMaxAI/MiniMax-M2

Text Generation • 229B • Updated Dec 23, 2025 • 195k • • 1.51k
stabilityai/sp4d

Updated Nov 5, 2025 • 125 • 15
Falconsai/text_summarization

Summarization • 60.5M • Updated Feb 17, 2024 • 19.8k • • 326
distil-whisper/distil-large-v3

Automatic Speech Recognition • 0.8B • Updated Apr 21 • 592k • 384

Video background removal

Running on Zero

Agents

Featured

367

Remove Video Background

🎞

367

Easily remove your videos background!

Architecture Related Models

Collection of models gathered together for my wife who is an architect (of buildings!)

Muapi/jj-s-architecture-office-building

Text-to-Image • Updated May 13 • 8 •
prithivMLmods/Canopus-Interior-Architecture-0.1

Text-to-Image • Updated Aug 4, 2024 • 147 • • 27

STT Fine Tune Resources

unsloth/whisper-large-v3

Automatic Speech Recognition • 2B • Updated May 14, 2025 • 3.71k • 20
unsloth/whisper-small

Automatic Speech Recognition • 0.2B • Updated May 14, 2025 • 1.25k • 7
unsloth/CrisperWhisper

Automatic Speech Recognition • 2B • Updated May 14, 2025 • 287 • 17
unsloth/whisper-large-v3-turbo

Automatic Speech Recognition • 0.8B • Updated May 14, 2025 • 4.2k • 13

Image to 3D

Running on Zero

MCP

764

TRELLIS

🏢

764

Scalable and Versatile 3D Generation from images

Concept Outlines

Running

2

Claude Agent Picker Pattern

🎯

2

Pattern for managing multi-agent crews in Claude Code

My Ideas

Running

2

Claude Agent Picker Pattern

🎯

2

Pattern for managing multi-agent crews in Claude Code

STT Evaluations

Sleeping

Agents

Local STT Eval One Sample

😻

Single sample eval for WER on various Whisper models
danielrosehill/Podcast-ASR-Evaluation

Viewer • Updated Nov 14, 2025 • 27 • 23
Sleeping

Agents

Podcast ASR Evaluation

🎙

ASR benchmark comparing local and cloud models
Running

STT Comparison

🦀

Comparing STT models against audio

Whisper Base + variants

openai/whisper-base

Automatic Speech Recognition • 72.6M • Updated Feb 29, 2024 • 1.62M • 306
openai/whisper-base.en

Automatic Speech Recognition • 72.6M • Updated Jan 22, 2024 • 151k • 58
onnx-community/whisper-base_timestamped

Automatic Speech Recognition • Updated Mar 5, 2025 • 33.2k • 32
Systran/faster-whisper-base

Automatic Speech Recognition • Updated Nov 23, 2023 • 1.61M • 46

Whisper variants

nyralabs/CrisperWhisper

Automatic Speech Recognition • 2B • Updated Jul 22 • 16.5k • 345

Voice Modality Apps

Runtime error

Agents

2

Voice Generated Visions

🦀

2

Cloud-Native Voice to-Image Generation using LLMs and GenAI

Entertainment Recommendations

Running

Agents

10

MovieReccomender

📚

10

Get a personalized recommendation using AI

Worlds (3D, Games)

Running on Zero

Agents

196

HunyuanWorld-Mirror

🌍

196

Universal 3D World Reconstruction with Any Prior Prompting

Proofs of Concept

Runtime error

Agents

Baby Noise Cancellation Demo

👶

AI-powered baby noise removal demo with STT comparison

Demos

Runtime error

Agents

Baby Noise Cancellation Demo

👶

AI-powered baby noise removal demo with STT comparison
Running

Nano Banana Sketch Cleanup

🎨

AI sketch cleanup with before/after comparisons

Deep Filter

Running

Agents

20

DeepFilterNet2 No File Size Limit

😻

20

Use DeepFilterNet2 to denoise audio no file size limit

Background Noise Removal

Runtime error

Agents

Baby Noise Cancellation Demo

👶

AI-powered baby noise removal demo with STT comparison
Running

Agents

186

DeepFilterNet2

💩

186

Denoise your recordings and view spectrograms
Running

Agents

20

DeepFilterNet2 No File Size Limit

😻

20

Use DeepFilterNet2 to denoise audio no file size limit

Gemini

Running

Gemini Vibe Coded POCs

🚀

Explore AI tools for productivity, creativity, analysis, and utilities

Vibe Coding

Running

Gemini Vibe Coded POCs

🚀

Explore AI tools for productivity, creativity, analysis, and utilities

Claude Code

Sleeping

Agents

Claude Code Slash Commands

⚡

Interactive browser for Claude Code slash commands
Running

1

Claude Code Linux Desktop Slash Commands

🖥

1

Slashes for Linux Desktop admin

Project Indexes

Running

AI Project Index

🏆

Navigable index of AI projects, tools, and agents
Running

Gemini Vibe Coded POCs

🚀

Explore AI tools for productivity, creativity, analysis, and utilities

Shakespeare AI

Just for fun projects for converting conventional text into Shakespearean English

Paused

Agents

Featured

30

Diffusion GPT

🖊

30

Generate Shakespearean text using a diffusion model
Runtime error

Shakespeare AI

😻

Rewrites .. stuff .. in Shakespearean English

AI UIs

Sleeping

Agents

Pen Pal AI

📮

Write letters and get thoughtful AI replies

Real Time Video To Video

Running on CPU Upgrade

Featured

105

Krea Realtime Video

👁

105

Generate AI videos from webcam, video, or text
krea/krea-realtime-video

Text-to-Video • 14B • Updated Sep 8 • 4.3k • 309

Voice Enhancement

Running

Agents

20

BroadcastAudioUpscaling

🌖

20

Enhance broadcast audio quality with super‑resolution upscaling
Running on Zero

Agents

64

Apollo

💻

64

Restore and enhance audio files with AI models

Multimodal AI

Sleeping

Agents

Multimodal AI Taxonomy

🌍
danielrosehill/multimodal-ai-taxonomy

Viewer • Updated Oct 22, 2025 • 85 • 76
Running

Gemini Vibe Coded POCs

🚀

Explore AI tools for productivity, creativity, analysis, and utilities

Taxonomies

Sleeping

Agents

Multimodal AI Taxonomy

🌍
danielrosehill/multimodal-ai-taxonomy

Viewer • Updated Oct 22, 2025 • 85 • 76

Context Utilities

Experimentary workflows (mostly) that aim to rethink how contextual data can be gathered to achieve personalised inference in AI systems

Sleeping

2

AI Context Generation Interviews

⚡

2

Model workflow using agents to proactively develop context
Sleeping

Agents

Context Cruncher

🎙

Transform voice recordings into structured AI context data

Veo 3.1

Running

Agents

601

veo3.1-fast

🐨

601

Generate videos from text prompts or images

Avatar Videos

Running on Zero

MCP

Featured

628

LatentSync

👄

628

Audio Conditioned LipSync with Latent Diffusion Models
Build error

Agents

Featured

1.43k

SadTalker

😭

1.43k

Generate a talking face video from an image and audio
Running

Agents

194

Gradio Lipsync Wav2lip

👄

194

Generate lip‑synced video from a face image and audio
Running

Agents

71

Wav2lip Gpu

🌍

71

Create a talking‑head video from a photo and audio

Architecture

benlehrburger/modern-architecture

Viewer • Updated May 31, 2023 • 1.09k • 590 • 4
Sleeping

Agents

2

ArchitectureClassifier

📈

2

Classify architectural styles in images
Running

Agents

17

Rocco Architecture Render

🚀

17

Generate interior and exterior designs from sketches
Sleeping

Agents

1

London Architecture

💻

1

Classify architectural styles in images

Resume Utilities

Runtime error

2

ATS Resume Checker

🌖

2

Parse resumes and match with job descriptions
Sleeping

Agents

2

Resume Matcher

🚀

2

Match resume with job description

Style Transfer

Running

367

SD Artists Browser

🤘

367

Explore artist styles and build SDXL prompts
Running on Zero

MCP

65

StyleAligned Transfer

🐠

65

Generate images in the style of a reference image
Paused

Agents

17

StyleFeatureEditor

💻

17

Edit images with predefined styles or text prompts
Runtime error

Agents

12

Kontext Style LoRAs

🌍

12

Transform images using selected styles

Multi LLM Experiments

Running on CPU Upgrade

60

Outsmart

🧠

60

Watch LLMs negotiate in a real‑time battle arena

Geolocation Utilities

Running on Zero

Agents

11

Location Predictor

🌍

11

Predict the location of any photo and view it on a map

Leaderboards

Running

22

AudioBench Leaderboard

🥇

22

View AudioBench leaderboard and compare model scores
Running

121

AI Phone Leaderboard

📱

121

AI Phone Leaderboard
Running

Agents

363

VBench Leaderboard

📊

363

Submit video model evaluation results to a public benchmark

Image Generation

Running on Zero

Agents

314

Sketch2lineart

🚀

314

Generate high‑quality lineart from your image

Object Detection

Running

Agents

Featured

101

Yolov10

📉

101

Detect objects in images with customizable YOLOv10 models

Security Tools

Running

Agents

28

GLiNER-Multi-PII

💻

28

Extract personally identifiable information from text

Text Processing Utilities

Running

Agents

28

GLiNER-Multi-PII

💻

28

Extract personally identifiable information from text
Sleeping

4

MarkItDown Microsoft

🐠

4

Extract Text in Structured Format

Developer Utilities

Running on Zero

Agents

Featured

932

Screenshot to HTML

⚡

932

Generate HTML code from a website screenshot

Data Visualization

Running

3

neulab/conala

🗺

3

Display interactive data visualizations

Medical

Running

3

Pharmacology Graph Explorer

💊

3

Explore predicted drug‑target and disease links
Running

Agents

76

Medical Diagnosis

📉

76

Classify symptoms to diagnose health issues
Running

29

MediAI Medical AI Agent

🚀

29

AI-Powered Diagnosis & Treatment Assistant
Sleeping

Agents

Lisdexamfetamine Split Dose Modeller

🚀

Model split-dose protocols for lisdexamfetamine/Vyvanse

Hugging Face Utilities

Sleeping

Agents

8

HF Downloader

📈

8

Download Hugging Face repositories to run locally.✔

CAD Utilities

Running on CPU Upgrade

Agents

Featured

138

SGS 1

🚀

138

Generate 3D CAD models from images

Scraping

Running

MCP

117

Web Scraper

🚀

117

Scrape a website and download its content as markdown

Subtitle generation

Sleeping

Agents

12

Whisper WebUI

🚀

12

Generate subtitles from audio or video files

Video editing utilities

Runtime error

Agents

31

LaMa Video Watermark Remover

🌖

31

Remove watermarks from videos
Sleeping

Agents

9

AudioDenoiser

👁

9

Remove background noise from videos
Paused

11

Image Video Colorization

🎥

11

Colorize black and white videos into full color

Game creation

Running

Featured

256

3D Game Maker

🏢

256

create games with AI

Audio editing utilities

Running

Agents

467

Remove Silence From Audio

🦀

467

Remove Silence From Audio
Running on Zero

Agents

415

Audio🔹Separator

🏃

415

Vocal and background audio separator
Running on Zero

Agents

Featured

330

Audio Editing

🎧

330

Edit audios with text prompts
Running on Zero

Agents

481

Resemble Enhance

🚀

481

Enhance your audio with denoising and quality boost

OSINT

Spaces and models that may have applications in open source intelligence (OSINT)

Running

157

Reverse Face Search

📉

157

Search Face Online
Runtime error

Agents

SATINT Analyst

👁

Professional satellite imagery intelligence analysis
Running on Zero

Agents

11

Location Predictor

🌍

11

Predict the location of any photo and view it on a map

Prompt engineering

Running

151

Prompt Lab

😻

151

Enhance your prompt into a structured, expert‑level version

Interesting ideas

AI use-cases and appliations that I found interesting (a repo for myself to explore!)

Running on Zero

Agents

Featured

2.32k

MagicQuill

🪶

2.32k

Edit images with sketches, colors, and text prompts
Build error

Agents

20

AutoPR

🚀

20

Generate a Twitter or Xiaohongshu post from a research PDF
Running

157

Reverse Face Search

📉

157

Search Face Online
Runtime error

Agents

16

AI STORYTELLER

🏢

16

Generate a video from a story

Data Processing Utilities

Running on Zero

Agents

679

MinerU Document Extraction Tools

📚

679

Embedded MinerU document extraction demo
Running

MCP

117

Web Scraper

🚀

117

Scrape a website and download its content as markdown
Running

Agents

105

PDF to Dataset

📄

105

Convert PDFs to a Hugging Face dataset

Background Removal

Running on Zero

MCP

2.97k

Background Removal

🌘

2.97k

Remove backgrounds from images instantly
Running on Zero

Agents

Featured

656

Video Background Removal

📽

656

Remove/Change background of video.
Running on Zero

Agents

974

BRIA RMBG 2.0

🐢

974

remove background from any image

Image To Video

Running on Zero

MCP

Featured

1.61k

LTX Video Fast

🎥

1.61k

ultra-fast video model, LTX 0.9.8 13B distilled

Image captioning

Salesforce/blip-image-captioning-base

Image-to-Text • Updated Feb 3, 2025 • 1.32M • 900

Video To Video

QuantStack/Wan2.2-Animate-14B-GGUF

Video-to-Video • 17B • Updated Sep 20, 2025 • 252k • 231

Video Generation Quants

QuantStack/Wan2.2-I2V-A14B-GGUF

Image-to-Video • 14B • Updated Jul 29, 2025 • 608k • 443

TTS With Dialog Support

nari-labs/Dia-1.6B

Text-to-Speech • 2B • Updated Jun 1, 2025 • 22.2k • • 2.93k

OCR & Document Processing

dots-studio/dots.ocr

Image-Text-to-Text • 3B • Updated Oct 31, 2025 • 762k • 1.34k
Runtime error

15

Ui Rev Doc Model

😻

15

Analysis of data on an invoice
Paused

Agents

Featured

145

Deepdoctection

🏃

145

Convert PDFs and images to structured text and layout data
Running

13

Docsifer

📚

13

Convert documents into clean, LLM-ready Markdown.

Diarisation

pyannote/speaker-diarization-community-1

Automatic Speech Recognition • Updated Sep 29, 2025 • 5.39M • 3.02k

Fast video generation

lightx2v/Wan2.2-Lightning

Text-to-Video • Updated Nov 13, 2025 • 91 • 637
ByteDance/AnimateDiff-Lightning

Text-to-Video • Updated Jan 6, 2025 • 25.3k • 1.01k

Long speech synthesis

microsoft/VibeVoice-1.5B

Text-to-Speech • 3B • Updated Jan 22 • 575k • 2.5k

Agentic code generation capable

Qwen/Qwen3-Coder-30B-A3B-Instruct

Text Generation • 31B • Updated Dec 3, 2025 • 439k • • 1.29k

Browser use capable

Qwen/Qwen3-Coder-30B-A3B-Instruct

Text Generation • 31B • Updated Dec 3, 2025 • 439k • • 1.29k

256K Context

Qwen/Qwen3-Coder-30B-A3B-Instruct

Text Generation • 31B • Updated Dec 3, 2025 • 439k • • 1.29k

Code Generation Models

Qwen/Qwen3-Coder-30B-A3B-Instruct

Text Generation • 31B • Updated Dec 3, 2025 • 439k • • 1.29k

Video Generation

chetwinlow1/Ovi

Image-to-Video • 12B • Updated Nov 15, 2025 • 71 • • 302
lightx2v/Wan2.2-Lightning

Text-to-Video • Updated Nov 13, 2025 • 91 • 637
Wan-AI/Wan2.2-T2V-A14B

Text-to-Video • Updated Aug 7, 2025 • 4.74k • • 577
QuantStack/Wan2.2-I2V-A14B-GGUF

Image-to-Video • 14B • Updated Jul 29, 2025 • 608k • 443

General LLM Quants

ai21labs/AI21-Jamba-Mini-1.7

52B • Updated Feb 2 • 287 • 44

Reasoning Models

ai21labs/AI21-Jamba-Reasoning-3B

Text Generation • 3B • Updated Oct 8, 2025 • 41k • 140
IFM/K2-Think

Text Generation • 33B • Updated Nov 19, 2025 • 231 • • 369
unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF

Text Generation • 8B • Updated Jun 16, 2025 • 109k • 466

Embedding Models

google/embeddinggemma-300m

Sentence Similarity • 0.3B • Updated Sep 25, 2025 • 3.03M • • 2.03k
nvidia/omni-embed-nemotron-3b

Sentence Similarity • 5B • Updated May 6 • 3.67k • 132
Qwen/Qwen3-Embedding-0.6B

Feature Extraction • 0.6B • Updated Apr 20 • 8.59M • • 1.29k
google/embeddinggemma-2

Feature Extraction • 0.7B • Updated 11 days ago • 151k • 2.52k

Instructional LLMs

LLMs optimised for instruction following rather than conversational use - quants and original models

meta-llama/Llama-3.1-8B-Instruct

Text Generation • 8B • Updated Sep 25, 2024 • 5.76M • • 8.46k
Qwen/Qwen3-Omni-30B-A3B-Instruct

Any-to-Any • 35B • Updated Sep 22, 2025 • 721k • 1.03k
moonshotai/Kimi-K2-Instruct-0905

Text Generation • 1T • Updated Jan 30 • 53.2k • • 790
mistralai/Mistral-7B-Instruct-v0.3

7B • Updated Dec 3, 2025 • 1.99M • 3.8k

Image Generation Models

tencent/HunyuanImage-3.0

Text-to-Image • 83B • Updated Jan 28 • 1.58k • • 1.15k
black-forest-labs/FLUX.1-schnell

Text-to-Image • 12B • Updated Aug 16, 2024 • 563k • • 6.3k
stabilityai/stable-diffusion-xl-base-1.0

Text-to-Image • 3B • Updated Oct 30, 2023 • 4.25M • • 8.35k
Qwen/Qwen-Image

Text-to-Image • 20B • Updated Aug 18, 2025 • 277k • • 2.67k

Deep research

FractalAIResearch/Fathom-Search-4B

Text Generation • 4B • Updated Oct 10, 2025 • 74 • • 122
Running

Agents

26

Fathom DeepResearch

📊

26

DeepResearch with the fathom search and synthesizer models

Image Generation Quants

Quantized versions of image generation models

lightx2v/Qwen-Image-Lightning

Text-to-Image • Updated Nov 3, 2025 • 259k • • 840

Mobile LLMs

LLMs optimised for running "on-device" (specifically, for this collection, on smartphones with standard inference capabilities)

facebook/MobileLLM-Pro

Text Generation • 1B • Updated Nov 11, 2025 • 8 • 164

LLMs

zai-org/GLM-4.6

Text Generation • 357B • Updated Sep 30, 2025 • 19.3k • • 1.24k

Agentic LLMs

zai-org/GLM-4.6

Text Generation • 357B • Updated Sep 30, 2025 • 19.3k • • 1.24k
AgentFlow/agentflow-planner-7b

8B • Updated Oct 12, 2025 • 542 • 64
HuggingFaceH4/zephyr-7b-beta

Text Generation • 7B • Updated Oct 16, 2024 • 91.3k • • 1.86k
zai-org/GLM-4.5-Air

Text Generation • 110B • Updated Aug 11, 2025 • 725k • • 646

Voice Cloning

neuphonic/neutts-air

Text-to-Speech • 0.7B • Updated Aug 26 • 1.83k • 906
coqui/XTTS-v2

Text-to-Speech • Updated Dec 11, 2023 • 6.19M • 3.89k
Running on Zero

Agents

102

Voice Cloning Studio

🚀

102

This space offers an easy-to-use interface for voice cloning

Local model collection

LLMs (mostly quants) that are small enough to run locally (on my hardware). My go-tos.

Qwen/Qwen3-VL-8B-Instruct

Image-Text-to-Text • 9B • Updated Oct 15, 2025 • 6.56M • • 1.21k
zai-org/GLM-4.6

Text Generation • 357B • Updated Sep 30, 2025 • 19.3k • • 1.24k
Qwen/Qwen3-VL-8B-Thinking

Image-Text-to-Text • 9B • Updated Nov 26, 2025 • 107k • • 229
meta-llama/Llama-3.1-8B-Instruct

Text Generation • 8B • Updated Sep 25, 2024 • 5.76M • • 8.46k

Vision Language Models

Qwen/Qwen3-VL-8B-Instruct

Image-Text-to-Text • 9B • Updated Oct 15, 2025 • 6.56M • • 1.21k
moondream/moondream3-preview

Image-Text-to-Text • 9B • Updated Apr 9 • 92.5k • 691

My Image Datasets

danielrosehill/Hebrew-Language-Signage

Viewer • Updated Nov 6, 2025 • 68 • 62
danielrosehill/Jerusalem-Streetscapes

Viewer • Updated Nov 6, 2025 • 413 • 33
danielrosehill/Tel-Aviv-Pics

Updated Nov 6, 2025 • 42
danielrosehill/Jerusalem-High-Rise-Development

Viewer • Updated Nov 6, 2025 • 56 • 76

Audio Datasets

danielrosehill/ai-generated-podcast-episodes

Viewer • Updated Aug 26, 2025 • 66 • 58 • 1
danielrosehill/Small-STT-Eval-Audio-Dataset

Viewer • Updated Dec 10, 2025 • 92 • 56
danielrosehill/Read-Aloud-Voice-Sentences

Viewer • Updated about 13 hours ago • 1.9k • 298
danielrosehill/English-Hebrew-Codeswitching-Sentences

Updated about 14 hours ago • 200

Datasets

danielrosehill/Zapier-Integrations-260825

Viewer • Updated Aug 26, 2025 • 8.64k • 19

Context Data

danielrosehill/Software-Wish-List-Context-Data

Updated Apr 28, 2025 • 21

Text Transformation

danielrosehill/Shakespearean-Text-Transformation-Prompts

Viewer • Updated Apr 21, 2025 • 1 • 28
danielrosehill/Speech-To-Text-System-Prompts-2

Viewer • Updated Apr 9, 2025 • 2 • 82 • 2
Sleeping

Agents

System Prompt Reformatter

📚

Reformats system prompts in the 2nd person and other edits
Sleeping

Agents

BLUF Email Formatter

📧

Format emails with clear subject lines and summaries

Experiments

danielrosehill/Long-Prompt-Experiment

Viewer • Updated Aug 19, 2025 • 92 • 82
Runtime error

Agents

AI Agent UN - Multi-Agent Simulation Framework

🏛

Explore UN voting simulations with AI agents
Sleeping

Max Output Tokens Analysis

📊

Display max output tokens for models over time

Evaluations

danielrosehill/ChatGPT-AI-Vs-API

Updated Apr 22, 2025 • 2
danielrosehill/Long-Prompt-Experiment

Viewer • Updated Aug 19, 2025 • 92 • 82
danielrosehill/STT-Voice-Notes-Evals

Updated Aug 11, 2025 • 194

AI Agents

AI agent network configs and projects

danielrosehill/Code-Gen-Agents-0925

Updated Sep 15, 2025 • 22
Runtime error

Agents

AI Agent UN - Multi-Agent Simulation Framework

🏛

Explore UN voting simulations with AI agents
Sleeping

Agents

Code Gen Agents Network

🔥

Code generation agent network with config navigator

Jerusalem

danielrosehill/Jerusalem-Emergency-Shelters-0925

Viewer • Updated Sep 19, 2025 • 149 • 17
danielrosehill/Jerusalem-Streetscapes

Viewer • Updated Nov 6, 2025 • 413 • 33
danielrosehill/Jerusalem-High-Rise-Development

Viewer • Updated Nov 6, 2025 • 56 • 76

Israel

Projects related to Israel

danielrosehill/Israel-Alerting-Zones

Preview • Updated May 9, 2025 • 28
danielrosehill/Tel-Aviv-Pics

Updated Nov 6, 2025 • 42
danielrosehill/Jerusalem-Streetscapes

Viewer • Updated Nov 6, 2025 • 413 • 33
danielrosehill/Jerusalem-Emergency-Shelters-0925

Viewer • Updated Sep 19, 2025 • 149 • 17

ISO Standards

ISO standard related projects

danielrosehill/ISO-3166-4217-Consolidated

Preview • Updated Sep 3, 2025 • 12

Reference / Lookup Datasets

danielrosehill/ISO-3166-4217-Consolidated

Preview • Updated Sep 3, 2025 • 12

Sustainability Projects

Datasets and projects related to sustainability esp impact investing

danielrosehill/GHG-Emissions-Data

Viewer • Updated Dec 20, 2024 • 78 • 189
danielrosehill/Global-Value-Factor-Database-Refactor-V2

Updated Sep 2, 2025 • 261
danielrosehill/ifvi_valuefactors_deriv

Updated Aug 21, 2025 • 263
danielrosehill/pay-for-outcomes-instruments

Preview • Updated May 21, 2025 • 11

Voice Note Audio And Training

Datasets for STT training, classification fine-tuning - especially voice notes

danielrosehill/Voice-Note-Audio

Preview • Updated Oct 27, 2025 • 128

Character Creation Datasets

Datasets for generating characters from 2D/3D

danielrosehill/Corn-The-Sloth

Viewer • Updated Apr 18, 2025 • 109 • 20

My System Prompt Collections

Collections of system prompts for assistants, agents, and workflows

danielrosehill/Data-Utils-System-Prompts

Updated Apr 9, 2025 • 48
danielrosehill/Email-Management-System-Prompts

Updated Apr 9, 2025 • 10
danielrosehill/General-Purpose-System-Prompts

Updated Apr 9, 2025 • 22 • 1
danielrosehill/Geopolitical-System-Prompts

Updated Apr 9, 2025 • 18

Israel Photo Galleries

Photo galleries of places in Israel for world generation use cases, among others

danielrosehill/Tel-Aviv-Pics

Updated Nov 6, 2025 • 42
danielrosehill/Jerusalem-High-Rise-Development

Viewer • Updated Nov 6, 2025 • 56 • 76

3D Human Digital Humans

Running on Zero

Agents

196

PSHuman

🏃

196

PHOTOREALISTIC HUMAN RECONSTRUCTION w/ CROSS-SCALE DIFF
Runtime error

Agents

11

Pifuhd

🐠

11

Generate 3D human models from images
Running on Zero

Agents

10

HumanWild

⚡

10

Generate 3D human reconstructions from images
Runtime error

51

HSMR

💀

51

Convert images of humans to biomechanically accurate 3D skeletons

3D-General

Running on Zero

Agents

Featured

2.3k

Hunyuan3D-2.1

👻

2.3k

Image-to-3D Generation
Running on Zero

MCP

764

TRELLIS

🏢

764

Scalable and Versatile 3D Generation from images
Running on Zero

Agents

3.41k

Hunyuan3D-2.0

🌍

3.41k

Text-to-3D and Image-to-3D Generation

Image To Image

Running on Zero

Agents

Featured

1.67k

Expression Editor

🐨

1.67k

Quickly edit the expression of a face
Running on Zero

Agents

Featured

1.54k

InstructPix2Pix

🚀

1.54k

Edit images using text instructions
Qwen/Qwen-Image-Edit-2509

Image-to-Image • 20B • Updated Sep 22, 2025 • 465k • • 1.26k
Qwen/Qwen-Image

Text-to-Image • 20B • Updated Aug 18, 2025 • 277k • • 2.67k

QR Art

Running on Zero

Agents

Featured

2k

QR Code AI Art Generator

📱

2k

QR Code AI Art Generator Blend QR codes with AI Art

Upscalers

Running on Zero

Agents

2.19k

Finegrain Image Enhancer

🖼

2.19k

Clarity AI Upscaler Reproduction
Running on Zero

Agents

183

RealESRGAN Pytorch

🔥

183

User Friendly Image & Video Upscaler!

Single Shot Image To Image (Reference)

Running on Zero

Agents

Featured

1.96k

PhotoMaker

📷

1.96k

Generate personalized photos of a person from a prompt

Speech To Text (STT)

Running on Zero

Agents

Featured

2.87k

Whisper

📉

2.87k

Transcribe audio or YouTube video into text
openai/whisper-large-v3

Automatic Speech Recognition • 2B • Updated Aug 12, 2024 • 3.72M • • 6.66k
ggerganov/whisper.cpp

Automatic Speech Recognition • Updated Oct 29, 2024 • 1.65k

Text To Speech (TTS)

Runtime error

Agents

Featured

2.76k

XTTS

🐸

2.76k

Generate speech from text using a reference voice
microsoft/VibeVoice-1.5B

Text-to-Speech • 3B • Updated Jan 22 • 575k • 2.5k
hexgrad/Kokoro-82M

Text-to-Speech • Updated Apr 10, 2025 • 10.4M • • 7.26k

Image To Video (No Audio)

Running on Zero

Agents

3.81k

Live Portrait

🤪

3.81k

Apply the motion of a video on a portrait
Running on Zero

MCP

Featured

2.04k

Stable Video Diffusion 1.1

📺

2.04k

Generate a short video from a single image
Running on Zero

MCP

Featured

1.62k

Wan2.1 Fast

🎥

1.62k

Animate an image into a short video using a text prompt

Music Generation

Running on Zero

Agents

Featured

5.11k

MusicGen

🎵

5.11k

Generate music from a text description and optional melody
suno/bark

Text-to-Speech • Updated Oct 4, 2023 • 25k • 1.58k
Running on L40S

Featured

753

Song Prep

🎵

753

Transcribe song lyrics with timestamps

Image Editing Utilities

Running on Zero

MCP

2.97k

Background Removal

🌘

2.97k

Remove backgrounds from images instantly
Running on Zero

Agents

2.98k

CLIP Interrogator

🕵

2.98k

Generate detailed prompts from any image
Paused

Agents

441

NoWatermark

⚡

441

Powerful Watermark Removal API
Running

Agents

142

Vectorizer AI

🌍

142

Convert images to SVG vectors with customizable settings

Character-Generation

Running on Zero

Agents

196

PSHuman

🏃

196

PHOTOREALISTIC HUMAN RECONSTRUCTION w/ CROSS-SCALE DIFF
Runtime error

MCP

11

3D Game Environment Builder

📚

11

3D Game Environment Builder MCP

Global Value Factor Database (GVFD) - Visualisation And Data

Version controlled refactors for data analysis of the Global Value Factor Database (GVFD) by the International Foundation for Valuing Impacts (IFVI).

Sleeping

Agents

GVFD Navigator

📉

Data visualisation utility for GVFD by IFVI (unofficial)
danielrosehill/Global-Value-Factor-Database-Refactor-V2

Updated Sep 2, 2025 • 261
danielrosehill/ifvi_valuefactors_deriv

Updated Aug 21, 2025 • 263

AI Experiments

Experiments in AI and prompt engineering

Sleeping

Max Output Tokens Analysis

📊

Display max output tokens for models over time
Sleeping

Agents

1

LLM Long Output Experiment (Code Generation)

📈

1

Evaluating max single output length of code gen LLMs
Running

Single Shot Brevity Training

📈

Using one example to train an LLM for informational brevity
Sleeping

Agents

Local STT Eval One Sample

😻

Single sample eval for WER on various Whisper models

Text Reformatting Apps

Implementations of apps for simple text reformatting tasks

Sleeping

Agents

BLUF Email Formatter

📧

Format emails with clear subject lines and summaries
Runtime error

Agents

System Prompt Depersonaliser

😻

Converts personal system prompts for general use
Runtime error

Shakespeare AI

😻

Rewrites .. stuff .. in Shakespearean English

Useful-Models

modularai/Llama-3.1-8B-Instruct-GGUF

Text Generation • 8B • Updated Sep 9, 2024 • 7.28k • 17
MaziyarPanahi/WizardLM-2-7B-GGUF

Text Generation • 7B • Updated Apr 15, 2024 • 98k • 83
MaziyarPanahi/mathstral-7B-v0.1-GGUF

Text Generation • 7B • Updated Jul 16, 2024 • 97.1k • 8
MaziyarPanahi/phi-4-GGUF

Text Generation • 15B • Updated Jan 8, 2025 • 108k • 10

Hebrew AI Spaces

Spaces to do with Hebrew language AI

Running on CPU Upgrade

Agents

46

Hebrew LLM Leaderboard

🥇

46

Explore LLM benchmark leaderboard with searchable filters
Sleeping

Agents

Hebrew GPT Neo - Science Fiction and Fantasy

🧙

Generate Hebrew text for science fiction and fantasy stories
Running

Agents

מחולל נונסנס רובושאול

🤖

מחולל משפטים בסגנון ״חיות כיס״
Build error

Agents

Hebrew Sentiment

😻

Hebrew datasets

Datasets in Hebrew

imvladikon/hebrew_speech_coursera

Viewer • Updated May 5, 2023 • 21k • 421 • 10
imvladikon/hebrew_speech_kan

Viewer • Updated May 5, 2023 • 10k • 493 • 15
sivan22/hebrew-handwritten-dataset

Viewer • Updated May 8, 2023 • 5.09k • 44 • 16
imvladikon/hebrew_speech_campus

Viewer • Updated Nov 20, 2023 • 75.9k • 300 • 7

Benchmarks

Running on CPU Upgrade

Agents

Featured

1.5k

Open ASR Leaderboard

🏆

1.5k

Explore multilingual speech recognition model benchmarks
Running

Agents

34

Hebrew Transcription Leaderboard

🥇

34

Benchmarking Hebrew Speech-to-Text Models
Running

Agents

453

Agent Leaderboard

💬

453

Ranking of LLMs for agentic tasks

ASR Models

Collection of ASR models for customized STT model training

nvidia/parakeet-tdt-0.6b-v2

Automatic Speech Recognition • Updated Jun 29 • 194k • 1.56k
ibm-granite/granite-speech-3.3-8b

Automatic Speech Recognition • 9B • Updated Apr 2 • 13.1k • 171
nvidia/canary-qwen-2.5b

Automatic Speech Recognition • 3B • Updated Apr 21 • 46.3k • 470
facebook/omniASR-W2V-1B

Automatic Speech Recognition • Updated Nov 27, 2025 • 6

Vintage-LLMs

openai-community/gpt2

Text Generation • 0.1B • Updated Feb 19, 2024 • 16.2M • 4.26k

Fav-Code-Generation-Models

Qwen/Qwen2.5-Coder-32B-Instruct

Text Generation • 33B • Updated Jan 12, 2025 • 723k • • 2.18k
deepseek-ai/DeepSeek-V2.5-1210

Text Generation • 236B • Updated Dec 11, 2024 • 2.5k • 271

Hebrew Large Language Models

Language models supporting TTS (predominantly the text generation task). These are almost exclusively fine-tunes of Gemma, Mistral, or the Qwen models

GiliGold/Knesset-DictaBERT

Fill-Mask • 0.2B • Updated Dec 28, 2024 • 59 • 2
yam-peleg/Hebrew-Gemma-11B

Text Generation • 10B • Updated Mar 16, 2024 • 105 • 38
yam-peleg/Hebrew-Mistral-7B

Text Generation • 8B • Updated Apr 26, 2024 • 443 • 73
yam-peleg/Hebrew-Mistral-7B-200K

Text Generation • 8B • Updated May 6, 2024 • 55 • 15

LLM-Experiments

Sleeping

Agents

1

LLM Long Output Experiment (Code Generation)

📈

1

Evaluating max single output length of code gen LLMs
GiliGold/Knesset-DictaBERT

Fill-Mask • 0.2B • Updated Dec 28, 2024 • 59 • 2

Daniel Rosehill PRO

AI & ML interests

Recent Activity

Organizations

danielrosehill 's collections 191

Chatterbox-Multilingual-TTS

Decision 2.0: Open Foundation Decision Models

Can You Run It? LLM version

Whisper Hebrish

Open ASR Leaderboard

Asr Metrics

Agentic LLM Price Comparisons

TRELLIS

Claude Agent Picker Pattern

Voice Generated Visions

HunyuanWorld-Mirror

Baby Noise Cancellation Demo

Nano Banana Sketch Cleanup

Baby Noise Cancellation Demo

DeepFilterNet2

DeepFilterNet2 No File Size Limit

Gemini Vibe Coded POCs

AI Project Index

Gemini Vibe Coded POCs

Pen Pal AI

BroadcastAudioUpscaling

Apollo

Multimodal AI Taxonomy

veo3.1-fast

ArchitectureClassifier

Rocco Architecture Render

London Architecture

SD Artists Browser

StyleAligned Transfer

StyleFeatureEditor

Kontext Style LoRAs

Location Predictor

Sketch2lineart

GLiNER-Multi-PII

Screenshot to HTML

Pharmacology Graph Explorer

Medical Diagnosis

MediAI Medical AI Agent

Lisdexamfetamine Split Dose Modeller

SGS 1

Whisper WebUI

3D Game Maker

Reverse Face Search

SATINT Analyst

Location Predictor

MagicQuill

AutoPR

Reverse Face Search

AI STORYTELLER

Background Removal

Video Background Removal

BRIA RMBG 2.0

Ui Rev Doc Model

Deepdoctection