Instructions to use lazymonster/yobyt5-restoration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lazymonster/yobyt5-restoration with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="lazymonster/yobyt5-restoration")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("lazymonster/yobyt5-restoration")
model = AutoModelForSeq2SeqLM.from_pretrained("lazymonster/yobyt5-restoration", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lazymonster/yobyt5-restoration with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lazymonster/yobyt5-restoration"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lazymonster/yobyt5-restoration",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lazymonster/yobyt5-restoration

SGLang

How to use lazymonster/yobyt5-restoration with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "lazymonster/yobyt5-restoration" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lazymonster/yobyt5-restoration",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "lazymonster/yobyt5-restoration" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lazymonster/yobyt5-restoration",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lazymonster/yobyt5-restoration with Docker Model Runner:
```
docker model run hf.co/lazymonster/yobyt5-restoration
```

Yo-ByT5: Byte-Level Diacritic Restoration for Yorùbá

Yo-ByT5 is a fine-tune of google/byt5-small that restores Yorùbá diacritics (tone marks: acute ◌́, grave ◌̀, mid unmarked; underdots: ẹ, ọ, ṣ) to undiacritized text.

Developer: Gali Ahmad Samuel (lazymonster)
Language: Yorùbá (yo)
Task: Automatic Diacritic Restoration (ADR)
License: Apache 2.0

Quickstart

import unicodedata
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

model_id = "lazymonster/yobyt5-restoration"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSeq2SeqLM.from_pretrained(model_id)

text = "Eko ni kokoro aseyori."
inputs = tokenizer(text, return_tensors="pt", max_length=1024, truncation=True)
outputs = model.generate(inputs["input_ids"], max_length=1024, num_beams=1)

predicted = tokenizer.decode(outputs[0], skip_special_tokens=True)
predicted = unicodedata.normalize("NFC", predicted)
print(predicted)
# Ẹ̀kọ́ ni kọ́kọ́rọ́ àṣeyọrí.

Benchmark Results

Evaluated on the YAD Test Benchmark (3,330 sentences) using base-word Needleman-Wunsch sequence alignment and Unicode NFC normalization.

The Corrected Reference repairs 1,415 non-standard underdot codepoints (U+0329 to standard U+0323) in the raw YAD release.

Metric	Decoding	Official Reference	Corrected Reference
DER (Total)	Beam (`num_beams=5`)	10.58%	10.14%
DER (Total)	Greedy (`num_beams=1`)	10.45%	10.00%
CER	Beam (`num_beams=5`)	3.75%	3.48%
CER	Greedy (`num_beams=1`)	3.82%	3.55%
WER	Beam (`num_beams=5`)	16.03%	14.86%
WER	Greedy (`num_beams=1`)	16.11%	14.93%
DER-tone	Beam (`num_beams=5`)	8.93%	8.93%
DER-tone	Greedy (`num_beams=1`)	8.76%	8.76%
DER-underdot	Beam (`num_beams=5`)	6.12%	6.15%
DER-underdot	Greedy (`num_beams=1`)	5.66%	5.69%
WDER	Beam (`num_beams=5`)	16.88%	15.64%
WDER	Greedy (`num_beams=1`)	16.81%	15.58%
BLEU	Beam (`num_beams=5`)	0.6841	0.6841
BLEU	Greedy (`num_beams=1`)	0.6837	0.6837
ChrF	Greedy / Beam	0.8431	0.8431

Training Data

Dataset	Sentences	License
MENYO-20k (Yorùbá train split)	9,942	CC BY-NC 4.0
Biblica® Open Yorùbá Contemporary Bible 2017	36,371	CC BY-SA
Total Train	46,313
Validation Set	5,305

Training Procedure

Architecture: google/byt5-small (299.6M parameters)
Compute: Google Cloud TPU v6e-8
Optimizer: AdamW, linear decay, weight decay 0.01, gradient clip norm 0.5
Batch Size: Per-device batch 4, gradient accumulation 2 (effective global batch size 64)
Phase 1: Learning rate 2e-4, 300 warmup steps, 4 epochs
Phase 2: Learning rate 1e-4, 0 warmup steps, 4 epochs (released checkpoint)

Recommendations

Unicode normalization: Always normalize input and generated text to NFC before scoring or processing.
Chunking: Chunk inputs longer than 1024 bytes at sentence or clause boundaries.
Decoding: Greedy decoding is fast and accurate. Beam search (num_beams=5) offers slight quality gains on edit distance metrics.

Citation & License

License

Model weights: Apache 2.0
Training data: Subject to original licenses (MENYO-20k: CC BY-NC 4.0; Biblica: CC BY-SA)

Citation

@misc{gali2025yobyt5,
  author       = {Gali Ahmad, Samuel},
  title        = {Yo-ByT5: Byte-Level Diacritic Restoration for Yor\`ub\'a},
  year         = {2025},
  publisher    = {Hugging Face},
  howpublished = {\url{https://huggingface.co/lazymonster/yobyt5-restoration}}
}

Acknowledgments

Trained as a member of the HausaNLP Research Group with compute support from the Google TPU Research Cloud (TRC) program.

Downloads last month: 384

Safetensors

Model size

0.3B params

Tensor type

F32

Model tree for lazymonster/yobyt5-restoration

Base model

google/byt5-small

Finetuned

(334)

this model

lazymonster
/

yobyt5-restoration