MockingBird/models/encoder/config.py
2022-12-03 16:54:06 +08:00

46 lines
1.1 KiB
Python

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_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_datasets = {
"voxceleb1" : {
"train": ["VoxCeleb1/wav"],
"test": ["VoxCeleb1/test_wav"]
},
"voxceleb2" : {
"train": ["VoxCeleb2/dev/aac"],
"test": ["VoxCeleb2/test_wav"]
}
}
other_datasets = [
"LJSpeech-1.1",
"VCTK-Corpus/wav48",
]
anglophone_nationalites = ["australia", "canada", "ireland", "uk", "usa"]