Everything in the catalog

Live pretraining progress for OpenEuroLLM models

Automating Academic Illustration For AI Scientists

Converts an MP3 into text using Whisper.

Guzheng Performance Technique Recognizer

A 40mb voice-action model, running entirely on WASM.

Retrieve image model information and generate JSON data

Speech-to-text for Arabic audio.

Finds personal data such as names, addresses and IDs in text across languages with a zero-shot entity model.

Extract text from images, translate it and export the result to an Excel file.

Search for destinations and attractions with instant results.

Builds a travel itinerary around the interests you pick.

Builds day-by-day plans with budget, packing list and local tips.

Itinerary planner that adds weather and map information.

Turns an RGB video into a frame-aligned alpha matte.

Discriminator of Bel Canto and Chinese Folk Singing

Chinese Traditional Instrument Sound Retriever

Verbatim + intended transcripts with word-level timing

Erhu Performance Technique Recognizer

Frame-level guzheng playing technique detector

TTS demo for Irodori-TTS-500M-v2

Chinese Music Pentatonic Mode Detector

Phoebe Chubby~ Phoeba Chubby...

Reconstructs a 3D face model from a single photo of a person.

Visualize, edit & verify Qur'anic recitation timestamps