Anup Singh

Thanks @Chaanks. Do you plan to upload KMeans models with 1024 cluster centroids for HuBERT and WavLM? I am training the KMeans models for the same as you suggested; however,...

Hi @YannCabanes, I have two sets, each containing N sequences, X = {x_i} and Y={y_i}, i=1,.., N. Each x_i and y_i are of different lengths lx_i and ly_i, respectively, but...

Hi @poonehmousavi, I see there are multiple repos (LibriSpeech100, LibriSpeech960, LibriSpeech-100-360-500) at [speechbrain/SSL_Quantization](https://huggingface.co/speechbrain/SSL_Quantization/tree/main). I am specifically looking for tokenizers of Hubert and WavLM models. Could you please let me know...

Hi @poonehmousavi Thanks for the clarification. I noticed that when using the `hf_hub_download` function within the `load_kmeans` method of both the DiscreteHuBERT and DiscreteWavLM classes, the `subfolder` parameter appears to...

Thanks for your reply. I get the following error when executing: dist_comp.set_query(faiss.swig_ptr(x_norm[0])) ``` TypeError: in method 'DistanceComputer_set_query', argument 2 of type 'float const *' ``` I also tried the following,...