anaksor-ocr
Sokheng · Kit
Reads Khmer and English text from documents, receipts and photos of signs, using a detector for text lines and a recogniser for each line. Suits developers who…
Reads messages for a chess league bot and works out the command or the proposed game times, for people testing the Lichess4545 bot's language model.
Arboters NLU is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page, a zip of its files. Nothing in it runs by itself.
pip install -U huggingface_hub hf download migold/arboters-nlu --repo-type space --local-dir arboters-nlu cd arboters-nlu
Arboters NLU is a browser demo of the language-understanding model behind the Lichess4545 league bot. It has two modes. Command mode works out what a message to the bot is asking for. Scheduling thread mode reads a pairing conversation and tracks the game times the two players discuss. It runs on zero-a10g hardware at Hugging Face.
League organizers and developers who build or test chat bots for chess leagues.
| Industry | Who uses it | How they use it | Example |
|---|---|---|---|
| Chess leagues | League organizers | Check how the bot would read a member's message | Trying a notification request before it goes live |
| Software | Bot developers | Test the model on sample messages | Pasting a short scheduling chat |
| NLP research | Students of language understanding | See span marking on synthetic chat data | Reading which times the model marked |
If you want a model that turns times into calendar dates or applies league rules, you can skip it, because this one only marks spans.
| Use case | Who | What they get back |
|---|---|---|
| Check a command | Bot developers | The command the model finds, its purpose, its notification event and its arguments |
| Read a scheduling chat | League members | Which times were written and whether each was offered, accepted or taken back |
| Browse the commands | Organizers | A list of the 25 commands with the purpose of each |
Online, nothing needs installing. For a copy on your own computer you need a few things first.
pip install -U huggingface_hub hf download migold/arboters-nlu --repo-type space --local-dir arboters-nlu cd arboters-nlu pip install gradio pip install -r requirements.txt python app.py
Pick a mode at the top of the page. In Command mode, type one message for the bot with the bot's name left out. In Scheduling thread mode, start every line with white: or black: and paste the conversation. You can also paste emoji and lists, and one-click inserts add common ones.
white: can we do thu 19:00 or sat 14:00? black: sat works
| Tool | What it does |
|---|---|
| Command mode | Names the command in one message, or none, with its purpose, event and arguments |
| Scheduling thread mode | Marks the times mentioned, and whether later messages accept or withdraw them |
| Command list | Lists the 25 commands with the purpose of each |
| Inserts | Add common emoji, list templates and new white: or black: messages |
You choose Command mode and type "ping me when knight42 starts". The model answers which command that message is, what the command is for, which notification event it sets and what arguments it takes. For a pairing chat like the one above, it marks the two times offered and the one accepted.
NLU means natural language understanding, a program that works out what a message means. To start, pick Command mode and type one short request to the bot.
The model marks spans of text. It does not turn times into dates, and it does not apply league rules. Its training data was entirely synthetic, so messages from real members may look different from what it learned on.
Reads messages for a chess league bot and works out the command or the proposed game times, for people testing the Lichess4545 bot's language model.
Made by migold on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.
What it is: Arboters NLU is a browser demo of the language-understanding model behind the Lichess4545 league bot. It has two modes. Command mode works out what a message to the bot is asking for. Scheduling thread mode reads a pairing conversation and tracks the game times the two players discuss. It runs on zero-a10g hardware at Hugging Face.
Who it suits: League organizers and developers who build or test chat bots for chess leagues.
Industry | Who uses it | How they use it | Example
Chess leagues | League organizers | Check how the bot would read a member's message | Trying a notification request before it goes live
Software | Bot developers | Test the model on sample messages | Pasting a short scheduling chat
NLP research | Students of language understanding | See span marking on synthetic chat data | Reading which times the model marked
If you want a model that turns times into calendar dates or applies league rules, you can skip it, because this one only marks spans.
Where to use it:
Use case | Who | What they get back
Check a command | Bot developers | The command the model finds, its purpose, its notification event and its arguments
Read a scheduling chat | League members | Which times were written and whether each was offered, accepted or taken back
Browse the commands | Organizers | A list of the 25 commands with the purpose of each
How to set it up: Online, nothing needs installing. For a copy on your own computer you need a few things first.
pip install -U huggingface_hub
hf download migold/arboters-nlu --repo-type space --local-dir arboters-nlu
cd arboters-nlu
pip install gradio
pip install -r requirements.txt
python app.py
How to use it: Pick a mode at the top of the page. In Command mode, type one message for the bot with the bot's name left out. In Scheduling thread mode, start every line with white: or black: and paste the conversation. You can also paste emoji and lists, and one-click inserts add common ones.
white: can we do thu 19:00 or sat 14:00?
black: sat works
Tool | What it does
Command mode | Names the command in one message, or none, with its purpose, event and arguments
Scheduling thread mode | Marks the times mentioned, and whether later messages accept or withdraw them
Command list | Lists the 25 commands with the purpose of each
Inserts | Add common emoji, list templates and new white: or black: messages
Example: You choose Command mode and type "ping me when knight42 starts". The model answers which command that message is, what the command is for, which notification event it sets and what arguments it takes. For a pairing chat like the one above, it marks the two times offered and the one accepted.
For newcomers and experts: NLU means natural language understanding, a program that works out what a message means. To start, pick Command mode and type one short request to the bot.
The model marks spans of text. It does not turn times into dates, and it does not apply league rules. Its training data was entirely synthetic, so messages from real members may look different from what it learned on.
Pick Command or Scheduling thread mode
Type or paste the message or the chat
The model marks commands, times and intent
You read the result
Good to know:
Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.
README.md 5 KB
Listed Hugging Face Spaces in the same category that share the most tags with this one.
| Product | Likes | Built with | License | Last change |
|---|---|---|---|---|
| Arboters NLU This page | 1 | gradio | agpl-3.0 | |
| FLUX.1 [dev]Shares gradio | 9,583 | gradio | mit | |
| InstantIDShares gradio | 3,659 | gradio | apache-2.0 | |
| Chat With Janus-Pro-7BShares gradio | 2,036 | gradio | mit | |
| PhotoMakerShares gradio | 1,960 | gradio | apache-2.0 | |
| Z Image TurboShares gradio | 1,940 | gradio | apache-2.0 |
Sokheng · Kit
Reads Khmer and English text from documents, receipts and photos of signs, using a detector for text lines and a recogniser for each line. Suits developers who…
Qwen · Kit
Qwen2.5-7B-Instruct as GGUF files in eight quantization sizes, to chat with locally through llama.cpp. For people who want a capable 7.6B model on their own co…
ACE-Step · Kit
Generates music from text with a 4B diffusion decoder, 50 steps and guidance control, aiming for higher audio quality than the base. For creators with a GPU of…
alirezarezvani · Skill
Adds 411 ready-made skills for Claude Code and other coding agents, grouped by role from engineering and product to marketing, finance and compliance. Installs…
block · Kit
Self-hostable workspace where people and AI agents share the same rooms, built on a Nostr relay that logs every action as a signed event. For teams that want t…
backnotprop · Kit
Opens your AI coding agent's plans, specs and code changes in a browser so you can annotate or comment on them and send the feedback straight back to the agent.