---
title: Ottema
emoji: 🏢
colorFrom: blue
colorTo: pink
sdk: static
pinned: true
license: apache-2.0
---

# Ottema

**Open, specialized AI models for Brazilian Portuguese and reliable AI systems.**

We build open-source models that solve concrete production problems in Brazilian Portuguese. Our work focuses on **open-vocabulary information extraction**, **structured-output recovery for agents**, **speech recognition**, and **operational AI for real-world workflows**.

Based in Brazil. Open research, reproducible benchmarks, production-oriented models.

## Brazilian Portuguese Extraction

Open-vocabulary NER and evidence extraction for real PT-BR text — including noisy operational domains where standard models fail.

| Model | What it's for | Result |
|---|---|---|
| [`ottema/gliner2-ptbr-harem`](https://huggingface.co/ottema/gliner2-ptbr-harem) (v0.12b) | NER on journalistic/formal PT-BR. **Best entity F1** among compared models on HAREM. | entity F1 = 0.4749 (macro) / 0.4501 (micro), 4x faster than BERT-CRF |
| [`ottema/gliner2-ptbr`](https://huggingface.co/ottema/gliner2-ptbr) (v0.4) | Generalist NER for informal PT-BR (chat, atendimento, suporte). | entity F1 = 0.9976 on synthetic benchmark |
| [`ottema/gliner2-ptbr-ontoevidence`](https://huggingface.co/ottema/gliner2-ptbr-ontoevidence) (v0.18) | Ontology-guided evidence extraction with hard-negative rejection. First model to break the GLiNER2 "yes-man" failure mode. | F1 = 0.32 on OE test, avg 4.4 pred/text |
| [`ottema/gliner2-ptbr-ontoevidence-data`](https://huggingface.co/datasets/ottema/gliner2-ptbr-ontoevidence-data) | 2268 samples, 3 splits, multi-label spans + hard negatives. | Apache-2.0 |

> 💡 Also published as [`ottema/gliner2-ptbr-v23`](https://huggingface.co/ottema/gliner2-ptbr-v23) (same weights, 90+ downloads).

> Browse the full **Ottema Open Models** collection: [huggingface.co/collections/ottema/ottema/ottema-open-models-6a3600e6cc0bdc9c01dd68c8](https://huggingface.co/collections/ottema/ottema/ottema-open-models-6a3600e6cc0bdc9c01dd68c8)

## Reliable Agents

Small specialized models that recover structured output when the LLM fails — JSON, tool calls, schema-constrained generation.

| Model | What it does |
|---|---|
| [`ottema/structfix-codet5p-220m`](https://huggingface.co/ottema/structfix-codet5p-220m) | Repairs broken JSON/tool-call output from upstream LLMs against a target schema. 220M params, fast, deterministic. |
| [`ottema/structfix-bench`](https://huggingface.co/datasets/ottema/structfix-bench) | Benchmark: 250k examples of schema-guided generation with controlled noise and constraint coverage. |
| [`ottema/constraint-dsl`](https://huggingface.co/datasets/ottema/constraint-dsl) | Compact DSL for declaring typed constraints over JSON outputs. |

## Speech & Edge AI

Lightweight ASR and small models for resource-constrained deployment.

| Model | What it's for |
|---|---|
| [`ottema/stt_pt_quartznet15x5_ctc_small`](https://huggingface.co/ottema/stt_pt_quartznet15x5_ctc_small) | Research baseline / lightweight CPU ASR reference for PT-BR. See [Nemotron full-stack](https://huggingface.co/ottema) for current SOTA. |

## How we work

- **Open research, reproducible benchmarks.** Every model ships with training data, evaluation scripts, and ablations documented.
- **Production-oriented.** We optimize for the metric that matters in deployment: latency, label F1 on the user's actual distribution, hard-negative robustness.
- **Honest about failure modes.** We publish what didn't work (see the "yes-man problem" with OntoEvidence).
- **No private data.** All training data is either synthetic, openly licensed, or used for training only (not redistributed).

## Try it

- [`ottema/gliner2-ptbr-demo`](https://huggingface.co/spaces/ottema/gliner2-ptbr-demo) — interactive Gradio demo with model selection, label presets, and 7 example sentences spanning journalistic, informal, and operational Portuguese.
- [`ottema/structfix-demo`](https://huggingface.co/spaces/ottema/structfix-demo) — repair broken JSON / tool-call output against typed schemas. 5 schema presets, 10 broken-output presets, 13 paired examples.

## Credits

Our models build on:
- **GLiNER / GLiNER2** (Urchade Zaratiana et al.) — open-vocabulary NER architecture
- **fastino/gliner2-multi-v1** (Fastino) — multilingual GLiNER2 base
- **microsoft/mdeberta-v3-base** — multilingual encoder
- **CodeT5+** (Salesforce) — seq2seq for structured output repair
- **Linguateca HAREM, lfcc, arubenruben** — Portuguese NER datasets (training only)

## License

All models and datasets are released under **Apache-2.0** unless otherwise noted.

## Contact

Organization: [huggingface.co/ottema](https://huggingface.co/ottema)