willwade
/

byt5-p2g-multilingual-tiny

text2text-generation

phoneme-to-grapheme

text-generation-inference

Model card Files Files and versions

ByT5 multilingual P2G (tiny) — 17M params

Phoneme-to-grapheme inversion of the harmonized retrain. Input: <lang>: phoneme tokens. Output: word spelling. Trained on a 4.12M-pair harmonized corpus.

Results (4k stratified test sample)

	score
micro exact	0.397
macro exact	0.557

Files

HF-format weights at root (~70 MB)
onnx/ — validated encoder+decoder pair

Licence

CC BY-SA 4.0

Downloads last month: 39

Safetensors

Model size

17.9M params

Tensor type

F32

·

Model tree for willwade/byt5-p2g-multilingual-tiny

Base model

google/byt5-small

Quantized

(5)

this model