Spaces:
Running
Running
from dataclasses import dataclass | |
from enum import Enum | |
class Task: | |
benchmark: str | |
metric: str | |
col_name: str | |
# Select your tasks here | |
# --------------------------------------------------- | |
class Tasks(Enum): | |
# task_key in the json file, metric_key in the json file, name to display in the leaderboard | |
task0 = Task("lid", "acc", "LID") | |
task1 = Task("topic_classification", "acc", "TC") | |
task2 = Task("rc_qa", "acc", "RC-QA") | |
task3 = Task("nli", "acc", "NLI") | |
task4 = Task("machine_translation_xx_eng", "chrf", "MT (xx-en)") | |
task5 = Task("machine_translation_eng_xx", "chrf", "MT (en-xx)") | |
class SpeechTasks(Enum): | |
# task_key in the json file, metric_key in the json file, name to display in the leaderboard | |
task0 = Task("lid", "acc", "LID") | |
task1 = Task("topic_classification", "acc", "TC") | |
task2 = Task("rc_qa", "acc", "RC-QA") | |
task3 = Task("asr", "cer", "ASR") | |
task4 = Task("s2tt", "chrf", "S2TT") | |
NUM_FEWSHOT = 0 # Change with your few shot | |
# --------------------------------------------------- | |
# Your leaderboard name | |
TITLE = """<h1 align="center" id="space-title">mSTEB Leaderboard</h1>""" | |
# What does your leaderboard evaluate? | |
INTRODUCTION_TEXT = """ | |
This leaderboard has the results of evaluation of models on mSTEB benchmark. | |
""" | |
# Which evaluations are you running? how can people reproduce what you have? | |
LLM_BENCHMARKS_TEXT = f""" | |
## Reproducibility | |
To reproduce our results please look at the github page for mSTEB: | |
https://github.com/McGill-NLP/mSTEB | |
""" | |
EVALUATION_QUEUE_TEXT = """ | |
## Submit your results | |
Please provide the model name, csv file and select the appropriate result type to upload your evaluation results for mSTEB. | |
Kindly format the results in the same way as provided in the sample csv files below. | |
""" | |
CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results" | |
CITATION_BUTTON_TEXT = r""" | |
@misc{beyene2025mstebmassivelymultilingualevaluation, | |
title = {mSTEB: Massively Multilingual Evaluation of LLMs on Speech and Text Tasks}, | |
author = {Luel Hagos Beyene and Vivek Verma and Min Ma and Jesujoba O. Alabi | |
and Fabian David Schmidt and Joyce Nakatumba-Nabende and | |
David Ifeoluwa Adelani}, | |
year = {2025}, | |
eprint = {2506.08400}, | |
archivePrefix = {arXiv}, | |
primaryClass = {cs.CL}, | |
url = {https://arxiv.org/abs/2506.08400} | |
} | |
""" | |