modelscope / 3D-Speaker

A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

eres2net模型是否支持mp3

xztzmr opened this issue · comments

from modelscope.pipelines import pipeline
sv_pipline = pipeline(
task='speaker-verification',
model='damo/speech_eres2net_large_sv_zh-cn_3dspeaker_16k',
#model_revision='v1.0.5'
)
result = sv_pipline(['/mnt/workspace/a.mp3', '/mnt/workspace/b.mp3'])
执行这个命令16G显存满了

支持mp3格式输入,可能是因为你音频太长导致显存out of memory. 可以考虑缩减音频长度,因speech_eres2net_large_sv_zh-cn_3dspeaker_16k参数量较大,后续会上线其剪枝模型,敬请期待。

好的多谢