interesting Small (Vision) Language Models that might be useful for AI Engineering purposes
John Ho PRO
GF-John
AI & ML interests
None yet
Recent Activity
updated a collection 26 days ago
TTS updated a collection 26 days ago
TTS updated a collection 26 days ago
object-trackingOrganizations
-
PaddleOCR-VL Online Demo
π238Extract text, tables, formulas, and charts from images
-
DeepSeek OCR Demo
π448An interactive demo for the DeepSeek-OCR model.
-
LightOnOCR 2 1B Demo
π¨107Extract text from images or PDFs with OCR
-
Multimodal OCR2
π»140FireRed / Nanonets / Monkey / Thyme / Typhoon / SmolDocling
-
Florence 2
π835Perform image captioning, detection, OCR and more with Florenceβ2
-
Florence2 + SAM2
π₯515Segment and caption objects in images and videos
-
SAM2 Video Predictor
π₯115Segment objects in a video with clickβbased masks
-
SAM2 Video Predictor
π₯22Segment and track objects in videos
-
EasyControl Ghibli
π¦1.45kNew Ghibli EasyControl model is now released!!
-
akiyamasho/AnimeBackgroundGAN-Miyazaki
Image-to-Image β’ Updated β’ 25 -
Ghibli Multilingual Text-Rendering
π¦72Elevating Ghibli-style AI art beyond ChatGPT's capabilities.
-
EasyControl Ghibli
π¦44New Ghibli EasyControl model is now released!!
-
Parakeet-TDT-0.6b-V2
Β467Transcribe audio files with timestamps and download transcripts
-
Fast Whisper Turbo
β‘51Ultra-fast Whisper Turbo inference β‘
-
openai/whisper-large-v3-turbo
Automatic Speech Recognition β’ Updated β’ 4.93M β’ β’ 2.87k -
Realtime Whisper Turbo
π€―346Realtime implementation of Whisper large turbo
-
Cantonese TTS Text To Speech
π9Generate Cantonese speech from text
-
Cantonese TTS Playground
π₯4Generate speech from Cantonese text using selected or custom voice
-
Dia 1.6B
π―1.76kGenerate realistic dialogue from a script, using Dia!
-
Daily Paper Podcast
π81Generates a podcast about today's top trending paper.
interesting Small (Vision) Language Models that might be useful for AI Engineering purposes
-
PaddleOCR-VL Online Demo
π238Extract text, tables, formulas, and charts from images
-
DeepSeek OCR Demo
π448An interactive demo for the DeepSeek-OCR model.
-
LightOnOCR 2 1B Demo
π¨107Extract text from images or PDFs with OCR
-
Multimodal OCR2
π»140FireRed / Nanonets / Monkey / Thyme / Typhoon / SmolDocling
-
Parakeet-TDT-0.6b-V2
Β467Transcribe audio files with timestamps and download transcripts
-
Fast Whisper Turbo
β‘51Ultra-fast Whisper Turbo inference β‘
-
openai/whisper-large-v3-turbo
Automatic Speech Recognition β’ Updated β’ 4.93M β’ β’ 2.87k -
Realtime Whisper Turbo
π€―346Realtime implementation of Whisper large turbo
-
Florence 2
π835Perform image captioning, detection, OCR and more with Florenceβ2
-
Florence2 + SAM2
π₯515Segment and caption objects in images and videos
-
SAM2 Video Predictor
π₯115Segment objects in a video with clickβbased masks
-
SAM2 Video Predictor
π₯22Segment and track objects in videos
-
Cantonese TTS Text To Speech
π9Generate Cantonese speech from text
-
Cantonese TTS Playground
π₯4Generate speech from Cantonese text using selected or custom voice
-
Dia 1.6B
π―1.76kGenerate realistic dialogue from a script, using Dia!
-
Daily Paper Podcast
π81Generates a podcast about today's top trending paper.
-
EasyControl Ghibli
π¦1.45kNew Ghibli EasyControl model is now released!!
-
akiyamasho/AnimeBackgroundGAN-Miyazaki
Image-to-Image β’ Updated β’ 25 -
Ghibli Multilingual Text-Rendering
π¦72Elevating Ghibli-style AI art beyond ChatGPT's capabilities.
-
EasyControl Ghibli
π¦44New Ghibli EasyControl model is now released!!