embedder.pt with new dataset
Devid29 opened this issue · comments
Hi, if in case I wanted to use another dataset of audio files for the training and the test (not the one used here) the embedder.pt that I have to insert when I run "trainer.py" as I can generate it or which one I have to use ? Thank you
Generally, you can simply use the provided embedder.pt for all cases. Since the speaker vector extractor was trained on VoxCeleb2 dataset, it works well with various language/environments.
Seung-won Park
Undergraduate Student
Dept. of Physics and Astronomy & Computer Science Engineering
Seoul National University
yyyyy@snu.ac.kr | http://swpark.me
…________________________________
From: Devid29 <notifications@github.com>
Sent: Thursday, September 12, 2019 12:36:46 AM
To: mindslab-ai/voicefilter <voicefilter@noreply.github.com>
Cc: Subscribed <subscribed@noreply.github.com>
Subject: [mindslab-ai/voicefilter] embeddet.pt with new dataset (#19)
Hi, if in case I wanted to use another dataset of audio files for the training and the test (not the one used here) the embedder.pt that I have to insert when I run "trainer.py" as I can generate it or which one I have to use ? Thank you
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub<#19>, or mute the thread<https://github.com/notifications/unsubscribe-auth/ADGGC5R3YU7Y3PUFZ5GS4NLQJEGA5ANCNFSM4IVVT3WA>.
Ok thanks because the dataset I am using is in Italian and I didn't know if this could create problems. Thank you
Yes, there were no significant problem when I was trying to use it with Korean speech. Good luck on your testing with Italian speech!
Best, Seungwon
Thank you!