From 3df4ecd455cb10cd30076697c92db57786c0cf3a Mon Sep 17 00:00:00 2001 From: chenfeiyu Date: Wed, 30 Dec 2020 14:37:01 +0800 Subject: [PATCH] add README for transformer_tts, waveflow and wavenet --- examples/wavenet/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/wavenet/README.md b/examples/wavenet/README.md index 0224742..468c90a 100644 --- a/examples/wavenet/README.md +++ b/examples/wavenet/README.md @@ -37,7 +37,7 @@ If you want distributed training, set a larger `--nprocs` (e.g. 4). Note that di ## Synthesize -Synthesize waveform. We assume the `--input` is a directory containing several mel spectrogram(log magnitude) in `.npy` format. The output would be saved in `--output` directory, containing several `.wav` files with the same name as the mel spectrogram does. +Synthesize waveform. We assume the `--input` is a directory containing several mel spectrogram(normalized into range[0, 1)) in `.npy` format. The output would be saved in `--output` directory, containing several `.wav` files with the same name as the mel spectrogram does. `--checkpoint_path` should be the path of the parameter file (`.pdparams`) to load. Note that the extention name `.pdparmas` is not included here.