From 698ac7e7faff107be2d6d668ed189c22d600fe71 Mon Sep 17 00:00:00 2001
From: Sting <loic.allegre@ensiie.fr>
Date: Fri, 21 Jul 2023 13:10:41 +0200
Subject: [PATCH] Update README + plot_syls
---
README.md | 20 +++++++++++++++-----
plot_syls.py | 17 ++++++++++++-----
2 files changed, 27 insertions(+), 10 deletions(-)
diff --git a/README.md b/README.md
index 5adecf4..9471adb 100644
--- a/README.md
+++ b/README.md
@@ -73,17 +73,21 @@ Having a CUDA-capable GPU is optional, but can greatly reduce processing time in
## Autokara
-To execute AutoKara from scratch on a MKV video file :
+To use Autokara, you need :
+ - A media file of the song (video, or pre-extracted vocals)
+ - An ASS file with the lyrics, split by syllable
+
+To execute AutoKara on a MKV video file and an ASS file containing the lyrics (ASS will be overwritten):
```bash
-$ python autokara.py video.mkv output.ass
+$ python autokara.py video.mkv lyrics.ass
```
-To execute AutoKara with existing syl splits and line timings :
+To output to a different file (and keep the original) :
```bash
-$ python autokara.py video.mkv output.ass --ref reference.ass
+$ python autokara.py video.mkv lyrics.ass -o output.ass
```
-To execute AutoKara on a (pre-extracted) WAV vocals file :
+To execute AutoKara on a (pre-extracted) WAV (or OGG, MP3, ...) vocals file, pass the `--vocals` flag :
```bash
$ python autokara.py vocals.wav output.ass --vocals
```
@@ -110,6 +114,12 @@ Batch preprocessing (vocals + ASS extraction) of all videos in a directory :
$ ./preprocess_media.sh video_folder output_folder
```
+A visualization tool, mainly intended for debug.
+Does the same as autokara.py, but instead of writing to a file, plots a graphic with onset times, spectrogram, probability curves,...
+Does not work on video files, only separated vocals audio files
+```bash
+$ python plot_syls.py vocals.wav lyrics.ass
+```
diff --git a/plot_syls.py b/plot_syls.py
index 527c1e4..e869604 100644
--- a/plot_syls.py
+++ b/plot_syls.py
@@ -5,6 +5,7 @@ import re
import matplotlib.pyplot as plt
import scipy.signal as sg
import parselmouth
+import argparse
from autosyl.assUtils import getSyls, timeToDate, dateToTime
from autosyl.LyricsAlignment.wrapper import align, preprocess_from_file
@@ -19,11 +20,17 @@ from autosyl.LyricsAlignment.wrapper import align, preprocess_from_file
#
##############################################################################
-songfile = sys.argv[1]
-if(len(sys.argv) >= 3):
- reference_syls = getSyls(sys.argv[2])
-else:
- reference_syls = None
+
+parser = argparse.ArgumentParser(description='AutoKara - Automatic karaoke timing tool')
+parser.add_argument("vocals_file", type=str, help="The audio file to time")
+parser.add_argument("ass_file", type=str, help="The ASS file with lyrics to time")
+
+args = parser.parse_args()
+
+
+songfile = args.vocals_file
+reference_syls, line_meta = getSyls(sys.argv[2])
+
print(reference_syls)
--
GitLab