"""
Python file to store configuration and info, e.g., which language
to use for a particular datasetm or which language a model should be 
evaluated on.
"""

from fair_asr_code.config import ALL_DATASET_CONFIGS, MODEL2LANG_SUPPORT

LOCAL_RESULTS_DIR = "fair-asr-results"
SETUPS = [{"majority_group": "male_masculine", "minority_group": "female_feminine"}]


class DatasetHelper:
    def __init__(self):
        self.dataset_configs = ALL_DATASET_CONFIGS

    def get_dataset_names(self):
        return [config.name for config in self.dataset_configs]

    def get_dataset_ids(self):
        return [config.dataset_id for config in self.dataset_configs]

    @property
    def sanitized_dataset_ids(self):
        return [config.sanitized_id() for config in self.dataset_configs]


class ModelHelper:
    def __init__(self):
        self.models = list(MODEL2LANG_SUPPORT.keys())

    @property
    def sanitized_model_ids(self):
        return [model.replace("/", "--") for model in self.models]

    def get_common_langs(self):
        common_langs = set(MODEL2LANG_SUPPORT[self.models[0]])
        for model in self.models:
            common_langs = common_langs.intersection(set(MODEL2LANG_SUPPORT[model]))
        return list(common_langs)


# CITATION_BUTTON_LABEL = "Please use this bibtex to cite these results"
CITATION_BUTTON_TEXT = r"""@inproceedings{attanasio-etal-2024-twists,
    title = "Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps",
    author = "Attanasio, Giuseppe  and
      Savoldi, Beatrice  and
      Fucci, Dennis  and
      Hovy, Dirk",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.emnlp-main.1188",
    doi = "10.18653/v1/2024.emnlp-main.1188",
    pages = "21318--21340",
    abstract = "Current automatic speech recognition (ASR) models are designed to be used across many languages and tasks without substantial changes. However, this broad language coverage hides performance gaps within languages, for example, across genders. Our study systematically evaluates the performance of two widely used multilingual ASR models on three datasets, encompassing 19 languages from eight language families and two speaking conditions. Our findings reveal clear gender disparities, with the advantaged group varying across languages and models. Surprisingly, those gaps are not explained by acoustic or lexical properties. However, probing internal model states reveals a correlation with gendered performance gap. That is, the easier it is to distinguish speaker gender in a language using probes, the more the gap reduces, favoring female speakers. Our results show that gender disparities persist even in state-of-the-art models. Our findings have implications for the improvement of multilingual ASR systems, underscoring the importance of accessibility to training data and nuanced evaluation to predict and mitigate gender gaps. We release all code and artifacts at https://github.com/g8a9/multilingual-asr-gender-gap.",
}"""