Spaces:
Sleeping
Sleeping
File size: 3,524 Bytes
7e9eac8 ebb01fc 7e9eac8 ebb01fc 7e9eac8 ebb01fc 7e9eac8 ebb01fc 7e9eac8 ebb01fc 7e9eac8 ebb01fc 7e9eac8 ebb01fc 7e9eac8 |
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 |
# Copyright 2022-2023 Xiaomi Corp. (authors: Fangjun Kuang)
#
# See LICENSE for clarification regarding multiple authors
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from functools import lru_cache
import sherpa_onnx
from huggingface_hub import hf_hub_download
def get_file(
repo_id: str,
filename: str,
subfolder: str = ".",
) -> str:
model_filename = hf_hub_download(
repo_id=repo_id,
filename=filename,
subfolder=subfolder,
)
return model_filename
@lru_cache(maxsize=10)
def _get_vits_vctk(repo_id: str, speed: float) -> sherpa_onnx.OfflineTts:
assert repo_id == "csukuangfj/vits-vctk"
model = get_file(
repo_id=repo_id,
filename="vits-vctk.onnx",
subfolder=".",
)
lexicon = get_file(
repo_id=repo_id,
filename="lexicon.txt",
subfolder=".",
)
tokens = get_file(
repo_id=repo_id,
filename="tokens.txt",
subfolder=".",
)
tts_config = sherpa_onnx.OfflineTtsConfig(
model=sherpa_onnx.OfflineTtsModelConfig(
vits=sherpa_onnx.OfflineTtsVitsModelConfig(
model=model,
lexicon=lexicon,
tokens=tokens,
length_scale=1.0 / speed,
),
provider="cpu",
debug=False,
num_threads=2,
)
)
tts = sherpa_onnx.OfflineTts(tts_config)
return tts
@lru_cache(maxsize=10)
def _get_vits_zh_aishell3(repo_id: str, speed: float) -> sherpa_onnx.OfflineTts:
assert repo_id == "csukuangfj/vits-zh-aishell3"
model = get_file(
repo_id=repo_id,
filename="vits-aishell3.onnx",
subfolder=".",
)
lexicon = get_file(
repo_id=repo_id,
filename="lexicon.txt",
subfolder=".",
)
tokens = get_file(
repo_id=repo_id,
filename="tokens.txt",
subfolder=".",
)
tts_config = sherpa_onnx.OfflineTtsConfig(
model=sherpa_onnx.OfflineTtsModelConfig(
vits=sherpa_onnx.OfflineTtsVitsModelConfig(
model=model,
lexicon=lexicon,
tokens=tokens,
length_scale=1.0 / speed,
),
provider="cpu",
debug=False,
num_threads=2,
)
)
tts = sherpa_onnx.OfflineTts(tts_config)
return tts
@lru_cache(maxsize=10)
def get_pretrained_model(repo_id: str, speed: float) -> sherpa_onnx.OfflineTts:
if repo_id in chinese_models:
return chinese_models[repo_id](repo_id, speed)
elif repo_id in english_models:
return english_models[repo_id](repo_id, speed)
else:
raise ValueError(f"Unsupported repo_id: {repo_id}")
chinese_models = {
"csukuangfj/vits-zh-aishell3": _get_vits_zh_aishell3,
}
english_models = {
"csukuangfj/vits-vctk": _get_vits_vctk,
}
language_to_models = {
"Chinese": list(chinese_models.keys()),
"English": list(english_models.keys()),
}
|