Downloads · 30 days
9
16% of all-time downloads
Darayut/netra-nmt-small-diffusion
netra-nmt-small-diffusion is a translation model from Darayut. Use it when you need text moved from one language to another. It is set up for netra-nmt. The card lists the license as mit.
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 th…
Downloads · 30 days
9
16% of all-time downloads
All-time downloads
56
Public
Parameters
89.9M
361 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors180 MB · 99%
From the Hugging Face model README
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).
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("សួស្តី", direction="km2en"))
Files: model.safetensors (fp16 weights), config.json, spm_32k.model (SentencePiece tokenizer).