# ==================================================================================================
# DEEPFAKE AUDIO - encoder/config.py (Dataset Manifest & Corpora Configuration)
# ==================================================================================================
# 
# 📝 DESCRIPTION
# This module acts as the centralized registry for all speech datasets supported 
# by the Speaker Encoder. It defines the directory structures for LibriSpeech, 
# LibriTTS, VoxCeleb, and other major open-source corpora. These configurations 
# guide the preprocessing scripts in discovering and categorizing audio samples 
# for training and validation.
#
# 👤 AUTHORS
# - Amey Thakur (https://github.com/Amey-Thakur)
# - Mega Satish (https://github.com/msatmod)
#
# 🤝🏻 CREDITS
# Original Real-Time Voice Cloning methodology by CorentinJ
# Repository: https://github.com/CorentinJ/Real-Time-Voice-Cloning
#
# 🔗 PROJECT LINKS
# Repository: https://github.com/Amey-Thakur/DEEPFAKE-AUDIO
# Video Demo: https://youtu.be/i3wnBcbHDbs
# Research: https://github.com/Amey-Thakur/DEEPFAKE-AUDIO/blob/main/DEEPFAKE-AUDIO.ipynb
#
# 📜 LICENSE
# Released under the MIT License
# Release Date: 2021-02-06
# ==================================================================================================

# --- LIBRISPEECH MANIFEST ---
librispeech_datasets = {
    "train": {
        "clean": ["LibriSpeech/train-clean-100", "LibriSpeech/train-clean-360"],
        "other": ["LibriSpeech/train-other-500"]
    },
    "test": {
        "clean": ["LibriSpeech/test-clean"],
        "other": ["LibriSpeech/test-other"]
    },
    "dev": {
        "clean": ["LibriSpeech/dev-clean"],
        "other": ["LibriSpeech/dev-other"]
    },
}

# --- LIBRITTS MANIFEST ---
libritts_datasets = {
    "train": {
        "clean": ["LibriTTS/train-clean-100", "LibriTTS/train-clean-360"],
        "other": ["LibriTTS/train-other-500"]
    },
    "test": {
        "clean": ["LibriTTS/test-clean"],
        "other": ["LibriTTS/test-other"]
    },
    "dev": {
        "clean": ["LibriTTS/dev-clean"],
        "other": ["LibriTTS/dev-other"]
    },
}

# --- VOXCELEB MANIFEST (SPEAKER RECOGNITION) ---
voxceleb_datasets = {
    "voxceleb1" : {
        "train": ["VoxCeleb1/wav"],
        "test": ["VoxCeleb1/test_wav"]
    },
    "voxceleb2" : {
        "train": ["VoxCeleb2/dev/aac"],
        "test": ["VoxCeleb2/test_wav"]
    }
}

# --- MISCELLANEOUS CORPORA ---
other_datasets = [
    "LJSpeech-1.1",
    "VCTK-Corpus/wav48",
]

# --- LINGUISTIC CATEGORIZATION ---
anglophone_nationalites = ["australia", "canada", "ireland", "uk", "usa"]