From 22930be7a79fa66ab9bca7d362c8c66a717d5025 Mon Sep 17 00:00:00 2001 From: tnlin Date: Wed, 13 Mar 2024 15:51:22 +0800 Subject: [PATCH] Update readme.md --- spectra/readme.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/spectra/readme.md b/spectra/readme.md index 37a498a..9913b56 100644 --- a/spectra/readme.md +++ b/spectra/readme.md @@ -12,7 +12,7 @@ To pretrain our model from scratch, please first download our processed pretrain Then, download pre-trained WavLM and RoBERTa models from huggingface.co (optional), and run `scripts/train-960.sh` #### PT dataset description -The `transForV4.pkl` file includes a dataset of 358,268 audio-text pairs, each less than 10 seconds in duration, complete with precise timestamp alignment details. Here's what an example entry looks like: +The `transForV4.pkl` (in `spotify.tgz`) includes a dataset of 358,268 audio-text pairs, each less than 10 seconds in duration, complete with precise timestamp alignment details. Here's what an example entry looks like: ``` ['//spotify-960/0/0/show_002B8PbILr169CdsS9ySTH/0.npy',