-
hi @andi611
I am interested in using your speaker probing on Librispeech. Could you share a bit more about the train/test split files? Are they from train-100,360,960? Are speakers from test split…
-
Hi,
Thanks for the great code. I have one question when I read through the code.
In train.sh, it claims that the total number of speakers in the training set is 8199. I'm not sure how this numb…
-
Hi, thanks for this great work. I met a problem when I used the dataprep.py to download the Voxceleb data. When I run this python file, it got error as below:
**_HTTP request sent, awaiting respons…
-
I am trying to use the pre-trained ECAPA and Xvectors model other than AMI and VoxCeleb. Should I normalize the embedding with mean_var_norm_emb during embed every speaker with multi-files? either ECA…
-
Eg:VoxCeleb/aac/id00017/lvX8diWgriA/00187.m4a,
what do the "id00017" and "lvX8diWgriA" mean?
-
Traceback (most recent call last):
File "/home/acharyaece/PycharmProjects/Speaker_recog/voxceleb/vox2_aac2/dev/aac/trainSpeakerNet.py", line 285, in
main()
File "/home/acharyaece/PycharmPr…
-
I try to train the standard xvector model on VoxCeleb1 trainset using the script `runVoxceleb.sh` with 4 GPUs. And I completely use the default parameters in `runStandardXvector-voxceleb1.py` except f…
matln updated
3 years ago
-
i was use
"
from speechbrain.pretrained import SpeakerRecognition
verification = SpeakerRecognition.from_hparams(source="speechbrain/spkrec-ecapa-voxceleb",
score, prediction = verification.veri…
-
I have a question, why the augment data is so big, isn't it slow to train?Have you considered limiting the augment data size? like the voxceleb v2 done? thanks!
-
Hi, i'm trying to use speaker diarization. I got embedding matrix but how do i convert it back to words according to speakers.
`verification = SpeakerRecognition.from_hparams(source="speechbrain/sp…