Hugging Face's logo

Spaces:
amphion
/
PicoAudio
Running on Zero

App Files Community
2
PicoAudio
File size: 6,501 Bytes 
8c1bf05
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
import hashlib
import os
import urllib
import warnings

from tqdm import tqdm

CACHE_DIR = os.getenv("AUDIOLDM_CACHE_DIR", "~/.cache")

_RN50 = dict(
    openai="https://openaipublic.azureedge.net/clip/models/afeb0e10f9e5a86da6080e35cf09123aca3b358a0c3e3b6c78a7b63bc04b6762/RN50.pt",
    yfcc15m="https://github.com/mlfoundations/open_clip/releases/download/v0.2-weights/rn50-quickgelu-yfcc15m-455df137.pt",
    cc12m="https://github.com/mlfoundations/open_clip/releases/download/v0.2-weights/rn50-quickgelu-cc12m-f000538c.pt",
)

_RN50_quickgelu = dict(
    openai="https://openaipublic.azureedge.net/clip/models/afeb0e10f9e5a86da6080e35cf09123aca3b358a0c3e3b6c78a7b63bc04b6762/RN50.pt",
    yfcc15m="https://github.com/mlfoundations/open_clip/releases/download/v0.2-weights/rn50-quickgelu-yfcc15m-455df137.pt",
    cc12m="https://github.com/mlfoundations/open_clip/releases/download/v0.2-weights/rn50-quickgelu-cc12m-f000538c.pt",
)

_RN101 = dict(
    openai="https://openaipublic.azureedge.net/clip/models/8fa8567bab74a42d41c5915025a8e4538c3bdbe8804a470a72f30b0d94fab599/RN101.pt",
    yfcc15m="https://github.com/mlfoundations/open_clip/releases/download/v0.2-weights/rn101-quickgelu-yfcc15m-3e04b30e.pt",
)

_RN101_quickgelu = dict(
    openai="https://openaipublic.azureedge.net/clip/models/8fa8567bab74a42d41c5915025a8e4538c3bdbe8804a470a72f30b0d94fab599/RN101.pt",
    yfcc15m="https://github.com/mlfoundations/open_clip/releases/download/v0.2-weights/rn101-quickgelu-yfcc15m-3e04b30e.pt",
)

_RN50x4 = dict(
    openai="https://openaipublic.azureedge.net/clip/models/7e526bd135e493cef0776de27d5f42653e6b4c8bf9e0f653bb11773263205fdd/RN50x4.pt",
)

_RN50x16 = dict(
    openai="https://openaipublic.azureedge.net/clip/models/52378b407f34354e150460fe41077663dd5b39c54cd0bfd2b27167a4a06ec9aa/RN50x16.pt",
)

_RN50x64 = dict(
    openai="https://openaipublic.azureedge.net/clip/models/be1cfb55d75a9666199fb2206c106743da0f6468c9d327f3e0d0a543a9919d9c/RN50x64.pt",
)

_VITB32 = dict(
    openai="https://openaipublic.azureedge.net/clip/models/40d365715913c9da98579312b702a82c18be219cc2a73407c4526f58eba950af/ViT-B-32.pt",
    laion400m_e31="https://github.com/mlfoundations/open_clip/releases/download/v0.2-weights/vit_b_32-quickgelu-laion400m_e31-d867053b.pt",
    laion400m_e32="https://github.com/mlfoundations/open_clip/releases/download/v0.2-weights/vit_b_32-quickgelu-laion400m_e32-46683a32.pt",
    laion400m_avg="https://github.com/mlfoundations/open_clip/releases/download/v0.2-weights/vit_b_32-quickgelu-laion400m_avg-8a00ab3c.pt",
)

_VITB32_quickgelu = dict(
    openai="https://openaipublic.azureedge.net/clip/models/40d365715913c9da98579312b702a82c18be219cc2a73407c4526f58eba950af/ViT-B-32.pt",
    laion400m_e31="https://github.com/mlfoundations/open_clip/releases/download/v0.2-weights/vit_b_32-quickgelu-laion400m_e31-d867053b.pt",
    laion400m_e32="https://github.com/mlfoundations/open_clip/releases/download/v0.2-weights/vit_b_32-quickgelu-laion400m_e32-46683a32.pt",
    laion400m_avg="https://github.com/mlfoundations/open_clip/releases/download/v0.2-weights/vit_b_32-quickgelu-laion400m_avg-8a00ab3c.pt",
)

_VITB16 = dict(
    openai="https://openaipublic.azureedge.net/clip/models/5806e77cd80f8b59890b7e101eabd078d9fb84e6937f9e85e4ecb61988df416f/ViT-B-16.pt",
)

_VITL14 = dict(
    openai="https://openaipublic.azureedge.net/clip/models/b8cca3fd41ae0c99ba7e8951adf17d267cdb84cd88be6f7c2e0eca1737a03836/ViT-L-14.pt",
)

_PRETRAINED = {
    "RN50": _RN50,
    "RN50-quickgelu": _RN50_quickgelu,
    "RN101": _RN101,
    "RN101-quickgelu": _RN101_quickgelu,
    "RN50x4": _RN50x4,
    "RN50x16": _RN50x16,
    "ViT-B-32": _VITB32,
    "ViT-B-32-quickgelu": _VITB32_quickgelu,
    "ViT-B-16": _VITB16,
    "ViT-L-14": _VITL14,
}


def list_pretrained(as_str: bool = False):
    """returns list of pretrained models
    Returns a tuple (model_name, pretrain_tag) by default or 'name:tag' if as_str == True
    """
    return [
        ":".join([k, t]) if as_str else (k, t)
        for k in _PRETRAINED.keys()
        for t in _PRETRAINED[k].keys()
    ]


def list_pretrained_tag_models(tag: str):
    """return all models having the specified pretrain tag"""
    models = []
    for k in _PRETRAINED.keys():
        if tag in _PRETRAINED[k]:
            models.append(k)
    return models


def list_pretrained_model_tags(model: str):
    """return all pretrain tags for the specified model architecture"""
    tags = []
    if model in _PRETRAINED:
        tags.extend(_PRETRAINED[model].keys())
    return tags


def get_pretrained_url(model: str, tag: str):
    if model not in _PRETRAINED:
        return ""
    model_pretrained = _PRETRAINED[model]
    if tag not in model_pretrained:
        return ""
    return model_pretrained[tag]


def download_pretrained(url: str, root: str = os.path.expanduser(f"{CACHE_DIR}/clip")):
    os.makedirs(root, exist_ok=True)
    filename = os.path.basename(url)

    if "openaipublic" in url:
        expected_sha256 = url.split("/")[-2]
    else:
        expected_sha256 = ""

    download_target = os.path.join(root, filename)

    if os.path.exists(download_target) and not os.path.isfile(download_target):
        raise RuntimeError(f"{download_target} exists and is not a regular file")

    if os.path.isfile(download_target):
        if expected_sha256:
            if (
                hashlib.sha256(open(download_target, "rb").read()).hexdigest()
                == expected_sha256
            ):
                return download_target
            else:
                warnings.warn(
                    f"{download_target} exists, but the SHA256 checksum does not match; re-downloading the file"
                )
        else:
            return download_target

    with urllib.request.urlopen(url) as source, open(download_target, "wb") as output:
        with tqdm(
            total=int(source.info().get("Content-Length")),
            ncols=80,
            unit="iB",
            unit_scale=True,
        ) as loop:
            while True:
                buffer = source.read(8192)
                if not buffer:
                    break

                output.write(buffer)
                loop.update(len(buffer))

    if (
        expected_sha256
        and hashlib.sha256(open(download_target, "rb").read()).hexdigest()
        != expected_sha256
    ):
        raise RuntimeError(
            f"Model has been downloaded but the SHA256 checksum does not not match"
        )

    return download_target