Hugging Face's logo

Spaces:
chenxie95
/
Language-Audio-Banquet
Runtime error

App Files Community
Language-Audio-Banquet
File size: 6,401 Bytes
d572f56
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
import os.path
from typing import Mapping, Optional

import pytorch_lightning as pl

from core.data.base import from_datasets
from core.data.moisesdb.dataset import MoisesDBRandomChunkBalancedRandomQueryDataset, MoisesDBRandomChunkRandomQueryDataset, \
    MoisesDBDeterministicChunkDeterministicQueryDataset, \
    MoisesDBFullTrackDataset, MoisesDBVDBODeterministicChunkDataset, \
    MoisesDBVDBOFullTrackDataset, MoisesDBVDBORandomChunkDataset, \
    MoisesDBFullTrackTestQueryDataset
    
def MoisesDataModule(
    data_root: str,
    batch_size: int,
    num_workers: int = 8,
    train_kwargs: Optional[Mapping] = None,
    val_kwargs: Optional[Mapping] = None,
    test_kwargs: Optional[Mapping] = None,
    datamodule_kwargs: Optional[Mapping] = None,
) -> pl.LightningDataModule:
    if train_kwargs is None:
        train_kwargs = {}

    if val_kwargs is None:
        val_kwargs = {}

    if test_kwargs is None:
        test_kwargs = {}

    if datamodule_kwargs is None:
        datamodule_kwargs = {}

    train_dataset = MoisesDBRandomChunkRandomQueryDataset(
        data_root=data_root, split="train", **train_kwargs
    )

    val_dataset = MoisesDBDeterministicChunkDeterministicQueryDataset(
        data_root=data_root, split="val", **val_kwargs
    )

    test_dataset = MoisesDBDeterministicChunkDeterministicQueryDataset(
        data_root=data_root, split="test", **test_kwargs
    )

    datamodule = from_datasets(
        train_dataset=train_dataset,
        val_dataset=val_dataset,
        test_dataset=test_dataset,
        batch_size=batch_size,
        num_workers=num_workers,
        **datamodule_kwargs
    )

    datamodule.predict_dataloader = (  # type: ignore[method-assign]
        datamodule.test_dataloader
    )

    return datamodule

def MoisesBalancedTrainDataModule(
    data_root: str,
    batch_size: int,
    num_workers: int = 8,
    train_kwargs: Optional[Mapping] = None,
    val_kwargs: Optional[Mapping] = None,
    test_kwargs: Optional[Mapping] = None,
    datamodule_kwargs: Optional[Mapping] = None,
) -> pl.LightningDataModule:
    if train_kwargs is None:
        train_kwargs = {}

    if val_kwargs is None:
        val_kwargs = {}

    if test_kwargs is None:
        test_kwargs = {}

    if datamodule_kwargs is None:
        datamodule_kwargs = {}

    train_dataset = MoisesDBRandomChunkBalancedRandomQueryDataset(
        data_root=data_root, split="train", **train_kwargs
    )

    val_dataset = MoisesDBDeterministicChunkDeterministicQueryDataset(
        data_root=data_root, split="val", **val_kwargs
    )

    test_dataset = MoisesDBDeterministicChunkDeterministicQueryDataset(
        data_root=data_root, split="test", **test_kwargs
    )

    datamodule = from_datasets(
        train_dataset=train_dataset,
        val_dataset=val_dataset,
        test_dataset=test_dataset,
        batch_size=batch_size,
        num_workers=num_workers,
        **datamodule_kwargs
    )

    datamodule.predict_dataloader = (  # type: ignore[method-assign]
        datamodule.test_dataloader
    )

    return datamodule
    

def MoisesValidationDataModule(
    data_root: str,
    batch_size: int,
    num_workers: int = 8,
    val_kwargs: Optional[Mapping] = None,
    datamodule_kwargs: Optional[Mapping] = None,
    **kwargs
) -> pl.LightningDataModule:
    if val_kwargs is None:
        val_kwargs = {}

    if datamodule_kwargs is None:
        datamodule_kwargs = {}
        
    allowed_stems = val_kwargs.get("allowed_stems", None)
    
    assert allowed_stems is not None, "allowed_stems must be provided"
    
    val_datasets = []
    
    for allowed_stem in allowed_stems:
        kwargs = val_kwargs.copy()
        kwargs["allowed_stems"] = [allowed_stem]
        val_dataset = MoisesDBDeterministicChunkDeterministicQueryDataset(
            data_root=data_root, split="val", 
            **kwargs
        )
        
        val_datasets.append(val_dataset)

    datamodule = from_datasets(
        val_dataset=val_datasets,
        batch_size=batch_size,
        num_workers=num_workers,
        **datamodule_kwargs
    )

    datamodule.predict_dataloader = (  # type: ignore[method-assign]
        datamodule.val_dataloader
    )

    return datamodule

def MoisesTestDataModule(
    data_root: str,
    batch_size: int = 1,
    num_workers: int = 8,
    test_kwargs: Optional[Mapping] = None,
    datamodule_kwargs: Optional[Mapping] = None,
    **kwargs
) -> pl.LightningDataModule:
    if test_kwargs is None:
        test_kwargs = {}

    if datamodule_kwargs is None:
        datamodule_kwargs = {}
        
    allowed_stems = test_kwargs.get("allowed_stems", None)
    
    assert allowed_stems is not None, "allowed_stems must be provided"

    test_dataset = MoisesDBFullTrackTestQueryDataset(
        data_root=data_root, split="test",
        **test_kwargs
    )

    datamodule = from_datasets(
        test_dataset=test_dataset,
        batch_size=batch_size,
        num_workers=num_workers,
        **datamodule_kwargs
    )

    datamodule.predict_dataloader = (  # type: ignore[method-assign]
        datamodule.test_dataloader
    )

    return datamodule


def MoisesVDBODataModule(
    data_root: str,
    batch_size: int,
    num_workers: int = 8,
    train_kwargs: Optional[Mapping] = None,
    val_kwargs: Optional[Mapping] = None,
    test_kwargs: Optional[Mapping] = None,
    datamodule_kwargs: Optional[Mapping] = None,
):
    
    
    if train_kwargs is None:
        train_kwargs = {}

    if val_kwargs is None:
        val_kwargs = {}

    if test_kwargs is None:
        test_kwargs = {}

    if datamodule_kwargs is None:
        datamodule_kwargs = {}
        
    train_dataset = MoisesDBVDBORandomChunkDataset(
        data_root=data_root, split="train", **train_kwargs
    )
    
    val_dataset = MoisesDBVDBODeterministicChunkDataset(
        data_root=data_root, split="val", **val_kwargs
    )
    
    test_dataset = MoisesDBVDBOFullTrackDataset(
        data_root=data_root, split="test", **test_kwargs
    )
    
    predict_dataset = test_dataset
    
    datamodule = from_datasets(
        train_dataset=train_dataset,
        val_dataset=val_dataset,
        test_dataset=test_dataset,
        predict_dataset=predict_dataset,
        batch_size=batch_size,
        num_workers=num_workers,
        **datamodule_kwargs
    )
    
    return datamodule