OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

T-NER

T-NER is a PyTorch-based Python library for fine-tuning language models on named-entity recognition and evaluating models across domains and languages.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

T-NER — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use T-NER when an NER workflow needs transformer fine-tuning and evaluation across more than one domain or language, or when adapting a model with custom IOB-formatted annotations.

Who it is for

  • Python developers building or adapting named-entity recognition models.
  • Researchers comparing NER performance across datasets, domains, or languages.

Documented uses

  • Fine-tune a language model for named-entity recognition.
  • Evaluate an NER model across domains or languages.
  • Use public NER datasets or prepare custom annotated data in IOB format.
  • Run the repository's Colab examples for fine-tuning and evaluation, prediction, or multilingual workflows.
Before you choose

Requirements & limits

The library is available through pip and is released under the MIT license.

  • Custom datasets need one-word-per-line IOB annotations, blank-line sentence boundaries, and a label-to-index mapping.
  • The repository describes public datasets and multi-dataset concatenation with a unified entity-label set.
  • The README links to Colab workflows and says fine-tuned models can be deployed to a web app for visualization.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Format a custom NER dataset for T-NER

Prepare annotated examples in the custom-data format described by the repository.

Before you start

  • A custom NER dataset with sentence boundaries and entity labels.
  • A label-to-index mapping.

Steps

  1. Write one word per line.

  2. Add an IOB entity tag to each word, using O for words outside entities and B-/I- tags for entity types.

  3. Separate sentences with blank lines.

  4. Prepare a label2id mapping for the tags.

Expected outcome

A custom dataset formatted in the IOB style described for use with T-NER.

Guide limitations

  • These steps cover data formatting only, not loading the dataset, fine-tuning a model, or evaluating results.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
asahi417/tner · Official homepage title · retained in its source language
How we review sourcesSuggest a correction