You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
35 lines
1.1 KiB
35 lines
1.1 KiB
# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
|
|
#
|
|
# 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.
|
|
import numpy as np
|
|
from logs import LOGGER
|
|
|
|
from paddlespeech.cli.vector import VectorExecutor
|
|
|
|
vector_executor = VectorExecutor()
|
|
|
|
|
|
def get_audio_embedding(path):
|
|
"""
|
|
Use vpr_inference to generate embedding of audio
|
|
"""
|
|
try:
|
|
embedding = vector_executor(
|
|
audio_file=path, model='ecapatdnn_voxceleb12')
|
|
embedding = embedding / np.linalg.norm(embedding)
|
|
embedding = embedding.tolist()
|
|
return embedding
|
|
except Exception as e:
|
|
LOGGER.error(f"Error with embedding:{e}")
|
|
return None
|