Downloads · 30 days
10
10% of all-time downloads
abhinandansamal/nllb-200-distilled-600M-LoRA-finetuned-odia-german-bidirectional
nllb-200-distilled-600M-LoRA-finetuned-odia-german-bidirectional is a translation model from abhinandansamal. Use it when you need text moved from one language to another. It is set up for transformers. The card lists the license as apache-2.0.
This is an adapter-tuned version of facebook/nllb-200-distilled-600M specialized for bidirectional translation between Odia (oryOrya) and German (deuLatn).
Downloads · 30 days
10
10% of all-time downloads
All-time downloads
102
Public
Parameters
615M
1.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.2 GB · 97%
From the Hugging Face model README
This is an adapter-tuned version of facebook/nllb-200-distilled-600M specialized for bidirectional translation between Odia (ory_Orya) and German (deu_Latn).
This model was developed as part of a thesis project / research paper publication focused on effective fine-tuning strategies for low-resource language pairs within the journalistic domain. It was fine-tuned on a carefully constructed hybrid dataset, combining a larger set of high-quality, human-validated translations with a smaller set of machine-translated sentences to expand lexical, contextual and grammatical coverage.
Live Demo:
facebook/nllb-200-distilled-600MThe model was fine-tuned on a meticulously prepared parallel corpus. Initially, 3,676 unique parallel line pairs were collected. Each "line" in the corpus was designed to provide contextual information for the model, typically containing 2-3 sentences, although some lines consist of a single sentence.
The data originates from two specific Odia newspapers and encompasses a diverse range of news domains, including National, International, Lifestyle, Sports, Trade, Environmental, Science and Technology, Leisure, Commerce, Metro, State, and Editorial.
The curation process involved distinct quality control steps for each language:
Following this rigorous curation, the corpus was transformed into a final bidirectional training dataset, resulting in 7,352 distinct training instances. This was achieved by creating two training examples from each parallel pair, utilizing task-specific prefixes (translate Odia to German: and translate German to Odia:). The overall size of this dataset was carefully managed and selected as a practical upper limit dictated by the memory and computational constraints of the available single-GPU training environment (NVIDIA A100 on Google Colab Pro).
Here, you can check the dataset.
The model was fine-tuned using PyTorch and the Hugging Face Seq2SeqTrainer.
Key Hyperparameters:
per_device_train_batch_size=8 with gradient_accumulation_steps=2)fp16=True)gradient_checkpointing=TrueThe fine-tuned model's performance was rigorously evaluated against the original facebook/nllb-200-distilled-600M baseline and the fully fine-tuned facebook/nllb-200-distilled-600M models on a held-out test set composed partially (77%) of human-validated sentence pairs. I report scores across four standard machine translation metrics: BLEU (higher is better), chrF (higher is better), TER (Translation Edit Rate, where lower is better) and COMET (higher is better).
| Metric | Odia → German (Baseline) | Odia → German (Fully Fine-Tuned) | Odia → German (Adapter-Based Fine-Tuned) | German → Odia (Baseline) | German → Odia (Fully Fine-Tuned) | German → Odia (Adapter-Based Fine-Tuned) |
|---|---|---|---|---|---|---|
| BLEU | 22.0355 | 27.1802 | 29.6874 | 9.3467 | 14.8624 | 17.3023 |
| chrF++ | 43.3357 | 54.3083 | 55.8151 | 38.3720 | 43.4127 | 46.4467 |
| TER | 82.7669 | 64.5270 | 61.6111 | 97.6340 | 74.4360 | 68.7356 |
| COMET | -0.0285 | 0.5479 | 0.5310 | 0.1876 | 0.8167 | 0.8607 |
The evaluation compares three systems: the original facebook/nllb-200-distilled-600M baseline, a fully fine-tuned NLLB-200 model, and the LoRA adapter–based fine-tuned model. Results are reported on a held-out test set and measured using BLEU, chrF++, TER, and COMET.
Odia → German (Generating the High-Resource Language): Competitive & EfficientGerman → Odia (Generating the Low-Resource Language): LoRA is the Superior StrategyIn the challenging direction of generating the morphologically rich, low-resource language (Odia), the Adapter-Based (LoRA) model emerged as the clear winner, outperforming the Fully Fine-Tuned model across all four metrics.
The results show that the LoRA-based fine-tuned model offers a highly efficient and competitive alternative to full fine-tuning, achieving equal or better translation quality than a fully fine-tuned NLLB-200 model while being significantly more parameter- and compute-efficient.
The LoRA fine-tuned model was additionally evaluated against several contemporary state-of-the-art (SOTA) large language models, including Gemini 2.5 Pro, Claude Sonnet 4.5, and GPT-5, in both German→Odia and Odia→German translation directions. Results are reported using BLEU, chrF++, TER, and COMET on the same test set.
| Direction | Model | BLEU | chrF++ | TER | COMET |
|---|---|---|---|---|---|
| German -> Odia | LoRA Fine-tuned NLLB | 17.504817 | 46.465875 | 68.416419 | 82.312126 |
| German -> Odia | Gemini 2.5 Pro | 16.070632 | 46.295084 | 69.725982 | 83.606876 |
| German -> Odia | Claude Sonnet 4.5 | 14.871904 | 44.830348 | 73.445582 | 82.608897 |
| German -> Odia | GPT-5 | 8.073554 | 37.729930 | 80.103444 | 80.266220 |
| Odia -> German | LoRA Fine-tuned NLLB | 30.063955 | 56.019427 | 61.202014 | 81.950075 |
| Odia -> German | Gemini 2.5 Pro | 33.654729 | 62.205780 | 58.810573 | 86.796387 |
| Odia -> German | Claude Sonnet 4.5 | 32.025087 | 61.365033 | 60.394378 | 86.328290 |
| Odia -> German | GPT-5 | 29.923673 | 59.730667 | 64.086428 | 86.501465 |
German → Odia (Generating the Low-Resource Language):In the German-to-Odia direction, the LoRA fine-tuned model demonstrates competitive and, in several metrics, superior performance relative to much larger proprietary SOTA models.
These results highlight the effectiveness of LoRA fine-tuning for low-resource target-language generation, where the adapter-based model matches or exceeds the performance of significantly larger, closed-source models.
Odia → German (Generating the High-Resource Language):For Odia-to-German translation, proprietary SOTA models—particularly Gemini 2.5 Pro and Claude Sonnet 4.5—achieve the highest overall scores across most metrics, reflecting their strong general-purpose multilingual capabilities.
The results demonstrate that parameter-efficient fine-tuning with LoRA can narrow—and in some cases close—the gap between open multilingual models and large proprietary SOTA systems, while remaining transparent, reproducible, and cost-effective.
The easiest way to use this model is with the translation pipeline from the transformers library. The model was trained to be bidirectional, and you can control the translation direction by specifying the src_lang and tgt_lang during the call.
from transformers import pipeline
# Load the translation pipeline with your fine-tuned model
model_id = "abhinandansamal/nllb-200-distilled-600M-LoRA-finetuned-odia-german-bidirectional"
translator = pipeline("translation", model=model_id, device_map="auto")
# --- Example 1: Translate Odia to German ---
odia_text = "ଆଜି ପାଗ ବହୁତ ଭଲ ଅଛି।"
german_translation = translator(
odia_text,
src_lang="ory_Orya",
tgt_lang="deu_Latn"
)
print(f"Odia Input: {odia_text}")
print(f"German Output: {german_translation[0]['translation_text']}")
# Expected Output: Das Wetter ist heute sehr gut.
# --- Example 2: Translate German to Odia ---
german_text = "Wie ist deine Gesundheit?"
odia_translation = translator(
german_text,
src_lang="deu_Latn",
tgt_lang="ory_Orya"
)
print(f"\nGerman Input: {german_text}")
print(f"Odia Output: {odia_translation[0]['translation_text']}")
# Expected Output: ତୁମର ସ୍ବାସ୍ଥ୍ୟ ଅବସ୍ଥା କଣ?
Note: While the model was trained with task prefixes (translate Odia to German:), using the translation pipeline with src_lang and tgt_lang arguments is the cleaner, recommended method for inference, as it abstracts this detail away.
This model is primarily intended for translating journalistic text between Odia and German. Given its training on articles from various news domains (e.g., National, International, Lifestyle, Sports, Science and Technology), it is suitable for academic research, cross-lingual information retrieval from news sources, and as a supportive tool for language learners focusing on news-related content in this specific language pair.
Despite the constraints in computational resources (single-GPU training on an NVIDIA T4) and the specialized dataset size (7,352 bidirectional instances), this research has achieved significant positive outcomes, demonstrating the viability of adapting large models for low-resource pairs.
To further enhance the model's performance, generalizability, and address existing limitations, the following factors are key considerations for future development:
If you use this model or the associated methodology in your research, please cite the following thesis:
@mastersthesis{SamalThesis2025,
author = Abhinandan Samal,
title = Enhancing Contextual Understanding in Low-Resource Languages Using Multilingual Transformers,
school = IU International University of Applied Sciences,
year = 2025
}