From 779c6206bc1aabdf851bfacd6c310d2720509b93 Mon Sep 17 00:00:00 2001 From: Mirco Ravanelli Date: Sun, 13 Aug 2023 15:49:50 -0400 Subject: [PATCH] Update README.md --- recipes/AudioMNIST/diffusion/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/recipes/AudioMNIST/diffusion/README.md b/recipes/AudioMNIST/diffusion/README.md index bb02bd9923..76b8bc316a 100644 --- a/recipes/AudioMNIST/diffusion/README.md +++ b/recipes/AudioMNIST/diffusion/README.md @@ -65,10 +65,10 @@ python train.py hparams/train_latent.yaml --data_folder=your/data/folder The quality of the generated digit is lower with latent diffusion. The generated signals should, however, sounds like a digit. -## Checkpoints and Training logs +## Samples, checkpoints and Training logs The training scripts will produce results that can be found in the `/samples` directory after each training epoch. -The output folder containing the checkpoints and training logs for all the aforementioned experiments can be found here: +The output folder containing the generated samples, model checkpoints and training logs for all the aforementioned experiments can be found here: https://www.dropbox.com/sh/szpmkp8aok1nquf/AABziohiZ8UhYBJz5TXscu93a?dl=0 # **About SpeechBrain**