How can I resolve 'killed' problem?

taylorlu / Speaker-Diarization

speaker diarization by uis-rnn and speaker embedding by vgg-speaker-recognition

Apache License 2.0

470 stars 121 forks source link

How can I resolve 'killed' problem? #26

Closed nyongja closed 4 years ago

nyongja commented 4 years ago

I generated speaker embeddings to use 4 persons audio data you provided. And I tried "python train.py" but it says Killed in the terminial. How can I resolve this problem..?

taylorlu commented 4 years ago

The speaker embeddings should contain a huge dataset like VCTK, the 4 persons audio example only shows how to predict or generate speaker embedding by GhostVLAD model.