Anup Singh

Hello @dpwe, Thanks for providing a repository for the audio indexing. I am interested in using your implementation as a baseline system for my research work. Could you please provide...

In your code- 'IndianPines_DataSet_Preparation_Without_Augmentation.ipynb', you have taken the patch size to be 1. So if my patch size is greater than 1, how will it going to work for the...

Hi, Could you please let me know if there is a way to update trained indexes with an incoming new data? I am particularly interested in deploying the LSH index.

Soft DTW with ignore_padding_token

2

Hello, I have a batch of pairs of sequences. Each pair contains sequences of different lengths, which are padded to equal lengths. Is there a way to ignore these padded...

Issues regarding discrete WavLM and discrete HuBERT

7

### Describe the bug Hi, I am trying to extract tokens using the modules: `speechbrain.lobes.models.huggingface_transformers.discrete_wavlm module` and `speechbrain.lobes.models.huggingface_transformers.discrete_hubert module`, but neither seems to work due to missing model checkpoints in...

Memory issue due to A and B matrix computation

3

Hi, Thanks for providing the Mamba implementation. I would like to know if there is any workaround in the efficient computation of `deltaA` and `deltaB_u` that can avoid the GPU...

Hi @hkproj Why do you add dropout to the attention scores (line 110 in model.py)? Shouldn't you discard the dropout in the multihead attention block because you already add a...

inquiry related to DistanceComputer

2

Is there a way to compute the asymmetric distance of a query with respect to encoded (using PQ) database items? I figured out that I needed to use the `get_FlatCodesDistanceComputer`...

Hi, I am interested in learning codewords (not using EMA) that are L2-normalized and orthonormal with each other. To do so, I created the vector quantizer using the following configuration:...