From eeb0386ddc1617972ea3cb85108fb35d32ccf388 Mon Sep 17 00:00:00 2001 From: jrichter <jrichter@exchange.informatik.uni-hamburg.de> Date: Tue, 18 Jun 2024 08:20:15 +0200 Subject: [PATCH] update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 8f36068..893947e 100644 --- a/README.md +++ b/README.md @@ -54,7 +54,7 @@ To see all available training options, run `python train.py --help`. Note that t **Note:** - Our journal preprint [2] uses `--backbone ncsnpp`. -- For the 48 kHz model [3], use `--backbone ncsnpp_48k --spec_factor 0.065 --spec_abs_exponent 0.667 --sigma-min 0.1 --sigma-max 1.0 --theta 2.0` +- For the 48 kHz model [3], use `--backbone ncsnpp_48k --n_fft 1534 --hop_length 384 --spec_factor 0.065 --spec_abs_exponent 0.667 --sigma-min 0.1 --sigma-max 1.0 --theta 2.0` - Our Interspeech paper [1] uses `--backbone dcunet`. You need to pass `--n_fft 512` to make it work. - Also note that the default parameters for the spectrogram transformation in this repository are slightly different from the ones listed in the first (Interspeech) paper (`--spec_factor 0.15` rather than `--spec_factor 0.333`), but we've found the value in this repository to generally perform better for both models [1] and [2]. -- GitLab