hash2430

Hello. I am Sunghee Jung. I guess this repository is about image verification.. Any chance you are working on speaker verification version of this repo?

Mutlihead attention implementation

1

# Concatenate context vector with input (most important) result = t.cat([decoder_input, result], dim=-1) Excuse me. I don't think I have seen concatenating multiheads with original input when doing self-attention. Plus...

Things to check when testing with different DB

3

This might be a silly question so I willl begin with apology. I am new to speaker verification and I am trying to apply this repo for VoxCeleb1. DataLoading and...

I think you need to change utils.get_cossim() line 42 as follows from `if speaker_num == centroid_num:` to `if (speaker_num == centroid_num) and (hp.training):` because you do not want to recalculate...

Excuseme. Can you tell me what DB you have used for training the pretrained model? I might refer to your repository on my research paper and would like to know...

Does anyone know the EER of this repo?

1

Hi. I am looking for some speaker verification repo that gives decent EER. I have tried some open source speaker verifications but I haven't been able to find anything that...

안녕하세요 혹시 음성 DB는 비공개인가요?

1

안녕하세요 "Speech Intention Understanding in a Head-final Language: A Disambiguation Utilizing Intonation-dependency" 논문 재밌게 잘 보았습니다. 혹시 논문에서 언급된 음성 DB와 annotation은 비공개인가요??ㅠ

Minor issue with avg pooling

1

I could be wrong, since I normaly don't do speech verification. But in my case, if I run the training it gives following error when affine transform is done to...

I see annotations in build_tokenized_answer of DPOTrainer regarding llama tokenizer compatibility. """ Llama tokenizer does satisfy `enc(a + b) = enc(a) + enc(b)`. It does ensure `enc(a + b) =...