{ "config": { "query_token_id": "[unused0]", "doc_token_id": "[unused1]", "query_token": "[Q]", "doc_token": "[D]", "ncells": null, "centroid_score_threshold": null, "ndocs": null, "load_index_with_mmap": false, "index_path": null, "nbits": 2, "kmeans_niters": 4, "resume": false, "similarity": "cosine", "bsize": 64, "accumsteps": 1, "lr": 3e-6, "maxsteps": 500000, "save_every": null, "warmup": null, "warmup_bert": null, "relu": false, "nway": 2, "use_ib_negatives": false, "reranker": false, "distillation_alpha": 1.0, "ignore_scores": false, "model_name": null, "query_maxlen": 32, "attend_to_mask_tokens": false, "interaction": "colbert", "dim": 128, "doc_maxlen": 300, "mask_punctuation": true, "checkpoint": "colbert-ir\/colbertv2.0", "triples": null, "collection": [ "list with 10000 elements starting with...", [ "You definitely need some sort of software to filter out the noise. Some of the other answers here can address that. If you're still doing the recordings and need to stop the cell phone interference, use ferrite beads near the base of each speaker. By the way, just in case anyone is curious, these can be used for small desktop speakers, too.", "Audacity would work great to edit out the noise from the cell phone. It has a filter that you can give it a sample of the noise you want to remove and then you can apply it to the recording to remove (as best as it can) the sound from the recording. You will have to probably try it several times to get it right, and it won't remove it completely, but it should help quite a bit. Audacity also has several other filters and tools to help remove general noise from a recording which should help with the quality as well. Hope that helps.", "On systems where the superuser account is disabled, such as Mac OS X, su will not work; sudo -s will. Also, it appears there is no su -s available, at least on my machine." ] ], "queries": null, "index_name": "technology.dev.2bits", "overwrite": false, "root": "\/content\/experiments", "experiment": "notebook", "index_root": null, "name": "2023-09\/09\/22.13.58", "rank": 0, "nranks": 1, "amp": true, "gpus": 1 }, "num_chunks": 1, "num_partitions": 8192, "num_embeddings": 872574, "avg_doclen": 87.2574 }