Dataset Preview
Full Screen
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
500 Server Error: Internal Server Error for url: https://huggingface.co/api/datasets/mayurasandakalum/singlish-to-sinhala-dataset/branch/refs%2Fconvert%2Fparquet (Request ID: Root=1-67865906-144eaee62206563802a0db89;89fbd07e-f4d2-4136-9948-ed8645a0bf29) Internal Error - We're working hard to fix this as soon as possible!
Error code:   UnexpectedError

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

conversations
list
[ { "content": "yogyathama", "role": "user" }, { "content": "යෝග්‍යතම", "role": "assistant" } ]
[ { "content": "yogyatha", "role": "user" }, { "content": "යෝග්‍යතා", "role": "assistant" } ]
[ { "content": "yogya", "role": "user" }, { "content": "යෝග්‍ය", "role": "assistant" } ]
[ { "content": "yogini", "role": "user" }, { "content": "යෝගිනී", "role": "assistant" } ]
[ { "content": "yoghurt", "role": "user" }, { "content": "යෝගට්", "role": "assistant" } ]
[ { "content": "yoghat", "role": "user" }, { "content": "යෝගට්", "role": "assistant" } ]
[ { "content": "yogee", "role": "user" }, { "content": "යෝගී", "role": "assistant" } ]
[ { "content": "yogayehi", "role": "user" }, { "content": "යෝගයෙහි", "role": "assistant" } ]
[ { "content": "yogaya", "role": "user" }, { "content": "යෝගය", "role": "assistant" } ]
[ { "content": "yogat", "role": "user" }, { "content": "යෝගට්", "role": "assistant" } ]
[ { "content": "yogacharyabhumi", "role": "user" }, { "content": "යෝගාචාර්යභූමි", "role": "assistant" } ]
[ { "content": "yoga", "role": "user" }, { "content": "යෝග", "role": "assistant" } ]
[ { "content": "yodun", "role": "user" }, { "content": "යොදුන්", "role": "assistant" } ]
[ { "content": "yodhagene", "role": "user" }, { "content": "යොදාගැනේ", "role": "assistant" } ]
[ { "content": "yodha", "role": "user" }, { "content": "යෝධ", "role": "assistant" } ]
[ { "content": "yodayange", "role": "user" }, { "content": "යෝධයන්ගේ", "role": "assistant" } ]
[ { "content": "yodayaku", "role": "user" }, { "content": "යෝධයකු", "role": "assistant" } ]
[ { "content": "yodaya", "role": "user" }, { "content": "යොදය", "role": "assistant" } ]
[ { "content": "yodawanu", "role": "user" }, { "content": "යොදවනු", "role": "assistant" } ]
[ { "content": "yodawanne", "role": "user" }, { "content": "යොදවන්නෙ", "role": "assistant" } ]
[ { "content": "yodawana", "role": "user" }, { "content": "යොදවන", "role": "assistant" } ]
[ { "content": "yodawa", "role": "user" }, { "content": "යොදවා", "role": "assistant" } ]
[ { "content": "yodana", "role": "user" }, { "content": "යොදන", "role": "assistant" } ]
[ { "content": "yodamin", "role": "user" }, { "content": "යොදමින්", "role": "assistant" } ]
[ { "content": "yodai", "role": "user" }, { "content": "යොදයි", "role": "assistant" } ]
[ { "content": "yodagenim", "role": "user" }, { "content": "යොදාගැනිම්", "role": "assistant" } ]
[ { "content": "yodagene", "role": "user" }, { "content": "යොදාගැනේ", "role": "assistant" } ]
[ { "content": "yodagena", "role": "user" }, { "content": "යොදාගෙන", "role": "assistant" } ]
[ { "content": "yodagatha", "role": "user" }, { "content": "යොදාගත", "role": "assistant" } ]
[ { "content": "yodagath wita", "role": "user" }, { "content": "යොදා ගත්විට", "role": "assistant" } ]
[ { "content": "yodagath", "role": "user" }, { "content": "යොදාගත්", "role": "assistant" } ]
[ { "content": "yodaganune", "role": "user" }, { "content": "යොදාගැනුනේ", "role": "assistant" } ]
[ { "content": "yodaganu", "role": "user" }, { "content": "යොදාගනු", "role": "assistant" } ]
[ { "content": "yodaganna", "role": "user" }, { "content": "යොදාගන්නා", "role": "assistant" } ]
[ { "content": "yodaganiti", "role": "user" }, { "content": "යොදාගනිති", "role": "assistant" } ]
[ { "content": "yodaganini", "role": "user" }, { "content": "යොදාගැනිණි", "role": "assistant" } ]
[ { "content": "yodaganimin", "role": "user" }, { "content": "යොදාගනිමින්", "role": "assistant" } ]
[ { "content": "yodaganimata", "role": "user" }, { "content": "යොදාගැනීමට", "role": "assistant" } ]
[ { "content": "yodaganima", "role": "user" }, { "content": "යොදාගැනීම", "role": "assistant" } ]
[ { "content": "yodagani", "role": "user" }, { "content": "යොදාගනී", "role": "assistant" } ]
[ { "content": "yodaganeema", "role": "user" }, { "content": "යොදාගැනීම", "role": "assistant" } ]
[ { "content": "yodaganee", "role": "user" }, { "content": "යොදාගනී", "role": "assistant" } ]
[ { "content": "yodaageniimen", "role": "user" }, { "content": "යෙදාගැනීමෙන්", "role": "assistant" } ]
[ { "content": "yodaageniimata", "role": "user" }, { "content": "යොදාගැනිමට", "role": "assistant" } ]
[ { "content": "yodaagatha", "role": "user" }, { "content": "යොදාගත", "role": "assistant" } ]
[ { "content": "yodaaganii", "role": "user" }, { "content": "යොදාගනී", "role": "assistant" } ]
[ { "content": "yodaa", "role": "user" }, { "content": "යොදා", "role": "assistant" } ]
[ { "content": "yoda", "role": "user" }, { "content": "යොදා", "role": "assistant" } ]
[ { "content": "yochif", "role": "user" }, { "content": "යොචිෆ්", "role": "assistant" } ]
[ { "content": "yo", "role": "user" }, { "content": "යො", "role": "assistant" } ]
[ { "content": "ynwa", "role": "user" }, { "content": "යනව", "role": "assistant" } ]
[ { "content": "ynnesupiri", "role": "user" }, { "content": "යන්නේසුපිරි", "role": "assistant" } ]
[ { "content": "ynne", "role": "user" }, { "content": "යන්නෙ", "role": "assistant" } ]
[ { "content": "ynna", "role": "user" }, { "content": "යන්න", "role": "assistant" } ]
[ { "content": "ynn", "role": "user" }, { "content": "යන්න", "role": "assistant" } ]
[ { "content": "ynkm", "role": "user" }, { "content": "යනකම්", "role": "assistant" } ]
[ { "content": "yna", "role": "user" }, { "content": "යන", "role": "assistant" } ]
[ { "content": "ymak", "role": "user" }, { "content": "යමක්", "role": "assistant" } ]
[ { "content": "ylukmk", "role": "user" }, { "content": "යාලුකමටත්", "role": "assistant" } ]
[ { "content": "ylu", "role": "user" }, { "content": "යාලු", "role": "assistant" } ]
[ { "content": "ykow", "role": "user" }, { "content": "යකූ", "role": "assistant" } ]
[ { "content": "yko", "role": "user" }, { "content": "යකො", "role": "assistant" } ]
[ { "content": "yithuyi", "role": "user" }, { "content": "යුතුයි", "role": "assistant" } ]
[ { "content": "yiouthuwana", "role": "user" }, { "content": "යුතුවන", "role": "assistant" } ]
[ { "content": "yi", "role": "user" }, { "content": "යි", "role": "assistant" } ]
[ { "content": "yhatha", "role": "user" }, { "content": "යහත", "role": "assistant" } ]
[ { "content": "yeyu", "role": "user" }, { "content": "යැයි", "role": "assistant" } ]
[ { "content": "yeyo", "role": "user" }, { "content": "යැයි", "role": "assistant" } ]
[ { "content": "yeyi", "role": "user" }, { "content": "යැයි", "role": "assistant" } ]
[ { "content": "yewune", "role": "user" }, { "content": "යැවුණේ", "role": "assistant" } ]
[ { "content": "yewiya", "role": "user" }, { "content": "යැවිය", "role": "assistant" } ]
[ { "content": "yewime", "role": "user" }, { "content": "යැවීමේ", "role": "assistant" } ]
[ { "content": "yevimehi", "role": "user" }, { "content": "යැවීමෙහි", "role": "assistant" } ]
[ { "content": "yevima", "role": "user" }, { "content": "යැවීම", "role": "assistant" } ]
[ { "content": "yesusthumage", "role": "user" }, { "content": "යේසුතුමාගේ", "role": "assistant" } ]
[ { "content": "yesus", "role": "user" }, { "content": "සේසුස්", "role": "assistant" } ]
[ { "content": "yerusalamata", "role": "user" }, { "content": "යෙරුසලමට", "role": "assistant" } ]
[ { "content": "yepumak", "role": "user" }, { "content": "යැපුමක්", "role": "assistant" } ]
[ { "content": "yepuma", "role": "user" }, { "content": "යැපුම", "role": "assistant" } ]
[ { "content": "yepum", "role": "user" }, { "content": "යැපුම්", "role": "assistant" } ]
[ { "content": "yepiya", "role": "user" }, { "content": "යැපිය", "role": "assistant" } ]
[ { "content": "yepena", "role": "user" }, { "content": "යැපෙන", "role": "assistant" } ]
[ { "content": "yemen", "role": "user" }, { "content": "යෑමෙන්", "role": "assistant" } ]
[ { "content": "yeme", "role": "user" }, { "content": "යෑමේ", "role": "assistant" } ]
[ { "content": "yemata", "role": "user" }, { "content": "යෑමට", "role": "assistant" } ]
[ { "content": "yemanaya", "role": "user" }, { "content": "යේමනය", "role": "assistant" } ]
[ { "content": "yema", "role": "user" }, { "content": "යෑම", "role": "assistant" } ]
[ { "content": "yellow", "role": "user" }, { "content": "යෙලෝ", "role": "assistant" } ]
[ { "content": "yel", "role": "user" }, { "content": "යේල්", "role": "assistant" } ]
[ { "content": "yei", "role": "user" }, { "content": "යැයි", "role": "assistant" } ]
[ { "content": "yehi", "role": "user" }, { "content": "යෙහි", "role": "assistant" } ]
[ { "content": "yeh", "role": "user" }, { "content": "යේ", "role": "assistant" } ]
[ { "content": "yedunu", "role": "user" }, { "content": "යෙදුණු", "role": "assistant" } ]
[ { "content": "yedunai", "role": "user" }, { "content": "යෙදුනායි", "role": "assistant" } ]
[ { "content": "yedunaha", "role": "user" }, { "content": "යෙදුනහ", "role": "assistant" } ]
[ { "content": "yedunada", "role": "user" }, { "content": "යෙදුනද", "role": "assistant" } ]
[ { "content": "yeduna", "role": "user" }, { "content": "යෙදුනා", "role": "assistant" } ]
[ { "content": "yedumwalin", "role": "user" }, { "content": "යෙදුම්වලින්", "role": "assistant" } ]
[ { "content": "yedumwala", "role": "user" }, { "content": "යෙදුම්වල", "role": "assistant" } ]
[ { "content": "yedumen", "role": "user" }, { "content": "යෙදුමෙන්", "role": "assistant" } ]
End of preview.

Dataset Summary

The Singlish-to-Sinhala Dataset is a large-scale dataset designed to facilitate the translation and understanding of Romanized Sinhala (Singlish) text. It consists of over 7 million rows of Romanized Sinhala phrases alongside their Sinhala script equivalents. This dataset is particularly useful for tasks such as:

  • Translation from Singlish to Sinhala.
  • Building and evaluating NLP models for low-resource languages.
  • Fine-tuning conversational AI models.

This dataset is a reformatted version of the Swabhasha Romanized Sinhala Dataset. The original dataset comprises over 7 million entries, each containing a Romanized Sinhala phrase and its corresponding Sinhala script equivalent, formatted as "Singlish/Sinhala." In the Singlish-to-Sinhala Dataset, each entry has been transformed into a conversational format to better support tasks such as training conversational AI models.

Key Features

  • Dataset Name: Singlish-to-Sinhala Dataset
  • Rows: 7,122,355
  • Columns: conversations
  • License: None

Dataset Structure

Data Instances

Each instance in the dataset contains:

  • conversations: A list of dictionaries with content and role keys.

Example:

{
  "conversations": [
    {"content": "yoghurt", "role": "user"},
    {"content": "යෝගට්", "role": "assistant"}
  ]
}

Dataset Statistics

  • Total Rows: 7,122,355
  • Features: One column (conversations)
  • Languages: Romanized Sinhala (Singlish) and Sinhala Script

Usage

Loading the Dataset

The dataset can be easily loaded using the Hugging Face datasets library:

from datasets import load_dataset

dataset = load_dataset("mayurasandakalum/singlish-to-sinhala-dataset", split="train")
print(dataset)

Dataset Exploration

The dataset includes samples in a conversational format. Here's how you can explore the first few rows:

for i in range(5):
    print(dataset[i]["conversations"])

Output:

[
  {"content": "yoghurt", "role": "user"},
  {"content": "යෝගට්", "role": "assistant"}
]

DataLoader Example

For large-scale processing, the dataset can be wrapped in a PyTorch DataLoader:

from torch.utils.data import Dataset, DataLoader

class TextDataset(Dataset):
    def __init__(self, conversations):
        self.conversations = conversations

    def __len__(self):
        return len(self.conversations)

    def __getitem__(self, idx):
        return self.conversations[idx]

text_dataset = TextDataset(dataset["conversations"])
dataloader = DataLoader(text_dataset, batch_size=1024, num_workers=4)

Model Training

The dataset is suitable for training conversational AI models. Here’s an example preprocessing pipeline for model input:

def format_conversations(example):
    return {
        "input_text": example["conversations"][0]["content"],
        "target_text": example["conversations"][1]["content"]
    }

formatted_dataset = dataset.map(format_conversations)

Dataset Creation

Source

The dataset was derived from the Swabhasha Romanized Sinhala Dataset and reformatted to align in a conversational format. The original dataset comprises over 7 million entries, formatted as "Singlish/Sinhala," and this structured format enhances the dataset's applicability for machine translation, transliteration, and conversational AI tasks.

Processing Steps

  1. Loaded the raw dataset.
  2. Converted each "Singlish/Sinhala" pair into a structured conversation format.
  3. Batch processed using PyTorch DataLoader for scalability.
  4. Uploaded to Hugging Face using the push_to_hub API.

Citation

If you use this dataset, please cite it as follows:

@dataset{mayurasandakalum2025singlish,
  author = "Mayura Sandakalum",
  title = "Singlish-to-Sinhala Dataset",
  year = 2025,
  publisher = "Hugging Face",
  howpublished = "https://huggingface.co/datasets/mayurasandakalum/singlish-to-sinhala-dataset"
}

License

This dataset does not have a specific license associated with it.

Downloads last month
25