Inputs recorded at different sampling rate generate drastically different embeddings?
#15 opened about 1 month ago
by
anuragrawal
What feautes the model uses? MFCC of FBANK
#14 opened 2 months ago
by
SaltanatJanybekova
Import Error While Installing SpeechBrain
1
#12 opened 7 months ago
by
mueksh
Available model is much larger than model discussed in the paper
#11 opened 10 months ago
by
mcorb1
can we fine tune on custom data ?
#10 opened 11 months ago
by
pulkitmehtawork
Pretrained ECAPA-TDNN with 256 as output?
#9 opened over 1 year ago
by
Khumbaba
Update ECAPA-TDNN readme to add diarization link
#8 opened over 1 year ago
by
nauman
cosine distance score
#7 opened over 1 year ago
by
sirsam01
Sample code to load from local checkpoint
1
#6 opened over 1 year ago
by
naveenbc
Datasets used for training
#5 opened almost 2 years ago
by
fra1993
What task is the model for?
2
#3 opened almost 2 years ago
by
k3ybladewielder
Increase execution speed
1
#2 opened over 2 years ago
by
Krishna-Kalakonda
Speaker Identification on 8Khz voice
1
#1 opened over 2 years ago
by
giusarno