Downloads · 30 days
17
7% of all-time downloads
rayvex/nllb-200-distilled-600M-hin-kang-v2
nllb-200-distilled-600M-hin-kang-v2 is a translation model from rayvex. Use it when you need text moved from one language to another. The card lists the license as mit.
This is a fine-tuned version of facebook/nllb-200-distilled-600M for Hindi to Kangri translation.
Downloads · 30 days
17
7% of all-time downloads
All-time downloads
248
Public
Parameters
615M
9.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.5 GB · 99%
From the Hugging Face model README
This is a fine-tuned version of facebook/nllb-200-distilled-600M for Hindi to Kangri translation.
This model was trained on a curated parallel corpus of 49k Hindi-Kangri sentence pairs, with additional vocabulary and tokenizer extensions for kang_Deva support.
facebook/nllb-200-distilled-600Mhin_Deva (Hindi)kang_Deva (Kangri in Devanagari script)kang_DevaHindi → Kangri only (unidirectional)import torch
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
model_name = "cloghost/nllb-200-distilled-600M-hin-kang-v2"
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
device = 0 if torch.cuda.is_available() else -1
translator = pipeline(
"translation",
model=model,
tokenizer=tokenizer,
src_lang="hin_Deva",
tgt_lang="kang_Deva",
device=device
)
text = """मगर हिमाचली भाषा तो पहले से बोली जा रही है।
लोग सदियों से ही इसके संग जी रहे हैं।
पहाड़ी भाषा का इतिहास हिन्दी साहित्य के आदिकाल ,जिसे सिद्ध चारण काल के नाम से भी जानते हैं
"""
translation = translator(text)
Evaluated on a clean 5k sample held-out test set:
| Metric | Value |
|---|---|
| BLEU | 26.03 |
| BLEU-4 | 14.11 |
| ROUGE-1 | 4.73% |
| ROUGE-L | 4.76% |
| METEOR | 43.63% |
| BERTScore-F1 | 93.39% |
| BERT Precision | 93.42% |
| BERT Recall | 93.37% |
| ChrF | 53.93 |
| TER (↓ is better) | 56.96 |
| Empty Predictions | 0 |