AI Models
    Diacnet 1.0

    OlaverseDiacnet 1.0

    DiacNet family · open weights on Hugging Face.

    African-language diacritic and tone restoration powered by a multilingual ByT5 model, making text readable, searchable, and machine-usable.

    Safetensors
    T5
    Diacritization
    Byt5
    Text2text Generation
    Text Generation
    Yoruba
    Vi
    Igbo
    Hausa
    Pl
    Tr
    Pt
    Es
    Fr
    It
    Base: google/byt5-small
    Base: google/byt5-small
    Licence: apache-2.0
    0
    Likes
    1306
    Downloads
    Jul 2026
    Created

    Model Card

    Built for production use.

    Open-weights repository on Hugging Face

    Integrated ecosystem protocol tier.

    Compatible with Transformers library

    Integrated ecosystem protocol tier.

    Optimised for low-latency inference

    Integrated ecosystem protocol tier.

    Community engagement: 0 likes

    Integrated ecosystem protocol tier.

    Quick Start

    Use Diacnet 1.0, straight from its model card.

    example.py
    from the model card
    from transformers import AutoTokenizer, T5ForConditionalGeneration
    tok = AutoTokenizer.from_pretrained("olaverse/diacnet-1.0")
    model = T5ForConditionalGeneration.from_pretrained("olaverse/diacnet-1.0")
    text = "<yor> se eranko naa si gbo o?"
    inputs = tok(text, return_tensors="pt")
    output_ids = model.generate(**inputs, max_new_tokens=256)
    print(tok.decode(output_ids[0], skip_special_tokens=True))
    # ṣé ẹranko náà sì gbọ́ ọ?
    Model Card

    Official Repository README

    Dynamically loaded from Hugging Face

    Model card metadata is available on Hugging Face.

    Built with

    Transformers PyTorch Python
    Built by Olaverse Labs

    Ready to try Diacnet 1.0?

    African-language diacritic and tone restoration powered by a multilingual ByT5 model, making text readable, searchable, and machine-usable.

    Model Ecosystem

    Explore More Models