Closed Devid29 closed 5 years ago
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 GitHubhttps://github.com/mindslab-ai/voicefilter/issues/19?email_source=notifications&email_token=ADGGC5TX3UDR5TNXJD2SB5LQJEGA5A5CNFSM4IVVT3WKYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4HKYEIZQ, or mute the threadhttps://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!
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