YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
đ °ī¸ Akshara-ML â Malayalam Transliteration Model
Akshara-ML is a neural transliteration model that converts Manglish (Romanized Malayalam) into Malayalam script.
Developed by EnduraSolution, in association with Aksharakuppy.
⨠Features
- đ¤ Manglish â Malayalam transliteration
- ⥠Fast inference (greedy decoding)
- đ¯ High accuracy (beam search decoding)
- đ§ Transformer-based architecture
- đŽđŗ Built specifically for Malayalam language
đ§Ē Example
| Manglish | Malayalam |
|---|---|
| namaskaram | ā´¨ā´Žā´¸āĩā´ā´žā´°ā´ |
| sugam aano | ā´¸āĩā´ā´ ā´ā´Ŗāĩ |
| ente peru | ā´ā´¨āĩā´ąāĩ ā´Ēāĩā´°āĩ |
đ Usage (Python)
from model import build_model
from train import load_checkpoint
from dataset import load_vocab, get_inverse_vocab
from config import Config
import torch
# Load vocab
src_vocab = load_vocab("src_vocab.json")
tgt_vocab = load_vocab("tgt_vocab.json")
inv_vocab = get_inverse_vocab(tgt_vocab)
# Build model
model = build_model(len(src_vocab), len(tgt_vocab))
load_checkpoint("pytorch_model.bin", model)
model.eval()
def transliterate(text):
ids = [Config.SOS_IDX] + [src_vocab.get(c, Config.UNK_IDX) for c in text] + [Config.EOS_IDX]
src = torch.tensor([ids])
pred_ids = model.greedy_decode(src)
output = ""
for i in pred_ids:
if i == Config.EOS_IDX:
break
output += inv_vocab.get(i, "")
return output
print(transliterate("namaskaram"))
- Downloads last month
- 6
Inference Providers NEW
This model isn't deployed by any Inference Provider. đ Ask for provider support