From 6b7acee02fabff7ee1b42b31260603f51c3bc803 Mon Sep 17 00:00:00 2001 From: Alain Riou <36546630+aRI0U@users.noreply.github.com> Date: Mon, 16 Oct 2023 18:07:20 +0200 Subject: [PATCH] Re-upload broken images in README.md --- README.md | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index 0c7f373..633b184 100644 --- a/README.md +++ b/README.md @@ -6,7 +6,7 @@ This code is the implementation of the [PESTO paper](https://arxiv.org/abs/2309. that has been accepted at [ISMIR 2023](https://ismir2023.ismir.net/). **Disclaimer:** This repository contains minimal code and should be used for inference only. -If you want full implementation details or want to use PESTO for research purposes, take a look at ~~[this repository](https://github.com/aRI0U/pesto-full)~~ (work in progress). +If you want full implementation details or want to use PESTO for research purposes, take a look at ~~[this repository](https://github.com/aRI0U/pesto-full)~~ (coming soon!). ## Installation @@ -59,7 +59,8 @@ Alternatively, one can save timesteps, pitch, confidence and activation outputs Finally, you can also visualize the pitch predictions by exporting them as a `png` file (you need `matplotlib` to be installed for PNG export). Here is an example: - + + Multiple formats can be specified after the `-e` option. @@ -81,7 +82,8 @@ Additionally, audio files can have any sampling rate; no resampling is required. By default, the model returns a probability distribution over all pitch bins. To convert it to a proper pitch, by default, we use Argmax-Local Weighted Averaging as in CREPE: - + + Alternatively, one can use basic argmax of weighted average with option `-r`/`--reduction`. @@ -150,11 +152,11 @@ Note that batched predictions are available only from the Python API and not fro ## Performances -On [MIR-1K]() and [MDB-stem-synth](), PESTO outperforms other self-supervised baselines. +On [MIR-1K](https://zenodo.org/record/3532216#.ZG0kWhlBxhE) and [MDB-stem-synth](https://zenodo.org/records/1481172), PESTO outperforms other self-supervised baselines. Its performances are close to CREPE's, which has 800x more parameters and was trained in a supervised way on a vast dataset containing MIR-1K and MDB-stem-synth, among others. - + ## Speed benchmark @@ -165,7 +167,8 @@ granularity of the predictions, which can be controlled with the `--step_size` p Here is a speed comparison between CREPE and PESTO, averaged over 10 runs on the same machine. - + + - Audio file: `wav` format, 2m51s - Hardware: 11th Gen Intel(R) Core(TM) i7-1185G7 @ 3.00GHz, 8 cores -- GitLab