Prabhjot Kaur

Results 8 comments of Prabhjot Kaur

Is there a plan to add 'Punjabi' language dataset to the corpus?

I would be happy to contribute. What kind of resources are we looking for? Raw audios in Punjabi language or language translations pairs between Punjabi and any other language? Are...

NLP / GSLM: Did anyone succeed in making K-means clustering model? (S2U)

When I execute the following ``` TYPE='hubert' ACOUSTIC_MODEL_PATH=./examples/textless_nlp/gslm/speech2unit/checkpoints/hubert_base_ls960.pt \ LAYER=6 \ MANIFEST=./examples/wav2vec/manifest/libri100/train.tsv \ KM_MODEL_PATH=./examples/textless_nlp/gslm/speech2unit/kmeans_saved/hubert50_new.bin PYTHONPATH=. python examples/textless_nlp/gslm/speech2unit/clustering/cluster_kmeans.py \ --num_clusters $N_CLUSTERS \ --feature_type $TYPE \ --checkpoint_path $CKPT_PATH \ --layer $LAYER \...

The fairseq installation failed

Hi, I would suggest to use Linux (Ubuntu) OS. I ran into a similar error when trying to install a library on my Windows machine (The library I was trying...

[Speech to speech translation with discrete units] produce almost the same audios from different test audios during inference

Hi @tarudesu - I am also working on the same problem. So,far my results are consistent with your finding where I get the same audio prediction for all samples (without...

[Speech to speech translation with discrete units] produce almost the same audios from different test audios during inference

@Haoheya - I got the exact same error as yours. My .tsv files and dict.txt is formatted the same way as yours too.. I am actively trying to debug. I...

[Speech to speech translation with discrete units] produce almost the same audios from different test audios during inference

@Haoheya - I was able to fix the error in my case. In my case, the sample names under 'id' in the .tsv files for the multitask was not matching...

[Speech to speech translation with discrete units] produce almost the same audios from different test audios during inference

Hello @tarudesu, @LaHeriody - May I know what was your sample size for training and how many epochs did you have to train the model for? I am not getting...

[Speech to speech translation with discrete units] produce almost the same audios from different test audios during inference

@9seven - I have not seen this error. You may want to check the config.yaml file. The attribute input_feat_per_channel is defined there. In my case, it is set to 80....