netra-nmt (diffusion, experimental)

A non-autoregressive discrete-diffusion decoder variant of netra-nmt, same encoder-decoder size (~90M params) as the autoregressive model, trading some translation quality for fixed-cost, parallel CPU decoding (see the main repo README for the quality/latency comparison).

Usage

pip install netra-nmt
from netra_nmt import DiffusionTranslator
t = DiffusionTranslator(repo_id="Darayut/netra-nmt-small-diffusion", steps=10)
print(t.translate("Hello, how are you?", direction="en2km"))
print(t.translate("แžŸแžฝแžŸแŸ’แžแžธ", direction="km2en"))

Files: model.safetensors (fp16 weights), config.json, spm_32k.model (SentencePiece tokenizer).

Downloads last month
-
Safetensors
Model size
89.9M params
Tensor type
F16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support