Modularcomputing/Native-Bird

---

Table of Contents

1. Introduction
2. Model Summary
3. Model Downloads
4. Evaluation Results
5. Quick Start
6. Searching Real Document Collections
7. Limitations
8. Citation
9. Contact

1. Introduction

Native-Bird is a 768-dimensional multilingual sentence-embedding model fine-tuned from LaBSE for cross-lingual retrieval across Igbo, Hausa, Yoruba and English.

Its primary use case is native-language query → English document retrieval: a user describes what they are looking for in Igbo, Hausa or Yoruba, the indexed documents are written in English, and Native-Bird maps both into the same embedding space for semantic search.

Igbo query: “Neuklọs ahụ bụ ahụ ihe abụọ mejupụtara ya - neutrọn na protọn.”

English document: “The nucleus consists of two particles - neutrons and protons.”

Native-Bird is the text backbone of Native-Bird2, which extends the same space to images.

2. Model Summary

Architecture

Architecture	SentenceTransformer (LaBSE encoder → pooling → dense → normalize)
Base model	sentence-transformers/LaBSE
Embedding dimension	768
Max sequence length (training)	128 tokens
Similarity	Cosine
Languages	Igbo (ig), Hausa (ha), Yoruba (yo), English (en)

Training

Objective	Cached Multiple Negatives Ranking Loss (CachedMNRL)
Training pairs	76,150 native-language ↔ English pairs
Epochs	4
Per-device batch size	256 (CachedMNRL mini-batch 128)
Learning rate / schedule	2e-5, cosine, 10% warmup
Negatives	In-batch, NO_DUPLICATES sampling
Precision	BF16

3. Model Downloads

Model	Modality	Embedding dim	Download
Native-Bird	Text (ig / ha / yo / en)	768	🤗 Hugging Face
Native-Bird2	Text + Image	512	🤗 Hugging Face

4. Evaluation Results

Cross-lingual retrieval against an English corpus of 1,004 sentences, with 204 queries per language. Each query has one known matching English sentence. Two query variants are tested: clean (original text) and ASR-style noise (diacritics removed, lowercased, punctuation stripped, whitespace normalized).

Language	Query	LaBSE R@1	Native-Bird R@1	LaBSE MRR	Native-Bird MRR
Igbo	Clean	1.0000	1.0000	1.0000	1.0000
Igbo	ASR-style noise	0.9853	1.0000	0.9888	1.0000
Hausa	Clean	1.0000	1.0000	1.0000	1.0000
Hausa	ASR-style noise	0.9951	1.0000	0.9975	1.0000
Yoruba	Clean	0.9804	0.9804	0.9871	0.9902
Yoruba	ASR-style noise	0.9559	0.9804	0.9683	0.9867

Native-Bird reaches R@10 = 1.0000 in every setting (LaBSE: 0.9951 on noisy Igbo and Yoruba). Fine-tuning mainly improves robustness to transcription-style noise, which matters for voice and keyboard input without diacritics.

Direct Igbo → English retrieval examples

Igbo query	Top English result	Cosine
Mgbanwe n'ọdịdị na-agbakwunye ọdịdị kejenetiki ọhụrụ, ma nhọpụta na-ewepụ ya n'ogwu ọdịdị nke a kọwapụtara.	Mutation adds new genetic variation, and selection removes it from the pool of expressed variation.	0.7079
Neuklọs ahụ bụ ahụ ihe abụọ mejupụtara ya - neutrọn na protọn.	The nucleus consists of two particles - neutrons and protons.	0.7049
Enwere ọtụtụ ihe mere ha ji kara web prọgzi mma: ha na-agbanwe ụzọ trafik ịntanetị niile, ọ bụghị naanị http.	They are superior to web proxies for several reasons: They re-route all Internet traffic, not only http.	0.6774

5. Quick Start

pip install -U sentence-transformers torch

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("Modularcomputing/Native-Bird")

query = "Neuklọs ahụ bụ ahụ ihe abụọ mejupụtara ya - neutrọn na protọn."
documents = [
    "The nucleus consists of two particles - neutrons and protons.",
    "The liver is an organ responsible for many metabolic functions.",
    "Photosynthesis converts light energy into chemical energy.",
]

q = model.encode(query, normalize_embeddings=True)
d = model.encode(documents, normalize_embeddings=True)
scores = d @ q

for i in scores.argsort()[::-1]:
    print(f"{scores[i]:.4f}  {documents[i]}")

The matching English sentence should rank first.

6. Searching Real Document Collections

Do not embed a multi-page document as one vector. Split each document into passages of roughly 100–300 words with overlap, and store each passage embedding with its parent document ID.

Igbo / Hausa / Yoruba query
        ↓  Native-Bird encoder
768-d query vector
        ↓  cosine similarity (FAISS / vector DB)
English passage index
        ↓
Top-k passages → grouped by parent document

Intended applications: native-language search over English knowledge bases, cross-lingual RAG retrieval, multilingual educational search, and search over Nigerian institutional documents.

7. Limitations

• Embedding model, not a translator or generator. It represents text as vectors; it does not produce English answers.
• Sentence-level evaluation. Trained at 128 tokens and evaluated on sentences, so long documents need chunking. Scores do not guarantee the same accuracy on arbitrary long documents.
• Domain shift. Government, legal, medical and technical text can differ substantially from the benchmark; evaluate on your target domain before production use.
• Status: research / early release. The next validation step is a human-annotated benchmark of real Nigerian documents and real Igbo, Hausa and Yoruba information needs.

8. Citation

@misc{nativebird2026,
  title  = {Native-Bird: Cross-lingual Native-Language Embeddings for English Document Retrieval},
  author = {Akuegbo, Chima Emmanuel},
  year   = {2026},
  publisher = {Modular},
  howpublished = {\url{https://huggingface.co/Modularcomputing/Native-Bird}}
}

9. Contact

Questions, issues or collaboration: open a discussion on the Community tab.