This tutorial will show you how to use PANNs and Milvus to search the similarity audio items.
$ git clone https://github.com/zilliz-bootcamp/audio_search.git
$ cd audio_search/webserver/
$ pip install -r audio_requirements.txt
Before running the script, please modify the parameters in webserver/audio/common/config.py:
MILVUS_HOST | milvus service ip address | 127.0.0.1 |
MILVUS_PORT | milvus service port | 19530 |
MYSQL_HOST | mysql service ip | 127.0.0.1 |
MYSQL_PORT | mysql service port | 3306 |
MYSQL_USER | mysql user name | root |
MYSQL_PWD | mysql password | 123456 |
MYSQL_DB | mysql datebase name | mysql |
MILVUS_TABLE | default table name | milvus_audio |
$ cd webserver
$ python main.py
You can type 127.0.0.1:8002/docs
into your browser to see all the APIs.
You can download the sample game_sound.zip and insert it into the system.
The sound data in the zip archive is required to be in wav format.
You can pass in test.wav to find the result that is most similar to that sound.
If you need a front-end interface, please refer to https://zilliz.com/demos/.