Downloads · 30 days
26
13% of all-time downloads
thenlpresearcher/shalaka_fd_indictrans2-en-indic-dist-200M_finetuned_eng_Latn_to_mar_Deva
shalaka_fd_indictrans2-en-indic-dist-200M_finetuned_eng_Latn_to_mar_Deva is a translation model from thenlpresearcher. Use it when you need text moved from one language to another. It is set up for transformers. The card lists the license as mit.
This model is a fine-tuned version of ai4bharat/indictrans2-en-indic-dist-200M for English-to-Marathi machine translation. It was developed to address punctuation robustness, as presented in the paper: Assessing and I…
Downloads · 30 days
26
13% of all-time downloads
All-time downloads
200
Public
Parameters
212M
851 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors847 MB · 99%
From the Hugging Face model README
This model is a fine-tuned version of ai4bharat/indictrans2-en-indic-dist-200M for English-to-Marathi machine translation. It was developed to address punctuation robustness, as presented in the paper: Assessing and Improving Punctuation Robustness in English-Marathi Machine Translation.
This model follows Approach 2 (Direct Fine-tuning) described in the research. It is the Combined Finetuned (1x Punct) variant, where the base model was fine-tuned on the IITB-ENG-MAR dataset using a strategy that alternates between keeping and removing punctuation in the source English text. This helps the model implicitly learn context and resolve semantic ambiguities (e.g., distinguishing "Honey" as a name versus a substance) even when punctuation is missing.
The model is intended for English-to-Marathi translation tasks, particularly those involving informal or unpunctuated source text (like social media or speech transcripts) where standard models might struggle with meaning-changing ambiguities.
The model achieves the following results on the evaluation set:
The following hyperparameters were used during training: