paraformer-speaker inference pipeline

shixian.shi

2023-10-10 8a0930d682fe3206e0b41c694fc03d7d10c7eed2

1
2
3
4
5
6
from modelscope.hub.snapshot_download import snapshot_download
import sys
 
 
cache_dir = sys.argv[1]
model_dir = snapshot_download('damo/speech_xvector_sv-zh-cn-cnceleb-16k-spk3465-pytorch', cache_dir=cache_dir)