fix args
Browse files- README.md +1 -1
- landscape2soundscape.py +5 -5
README.md
CHANGED
@@ -42,7 +42,7 @@ Beta version of [SHIFT](https://shift-europe.eu/) TTS tool with [AudioGen sounds
|
|
42 |
Build virtualenv & run api.py
|
43 |
</summary>
|
44 |
|
45 |
-
Above
|
46 |
loading only once the TTS & AudioGen model.
|
47 |
|
48 |
Clone
|
|
|
42 |
Build virtualenv & run api.py
|
43 |
</summary>
|
44 |
|
45 |
+
Above [TTS Demo](https://huggingface.co/dkounadis/artificial-styletts2/blob/main/demo.py) is a standalone script that loads SHIFT TTS & AudioGen model(s) and synthesizes a txt. We also provide a Flask `api.py` that allows faster inference with
|
46 |
loading only once the TTS & AudioGen model.
|
47 |
|
48 |
Clone
|
landscape2soundscape.py
CHANGED
@@ -2,7 +2,7 @@ import numpy as np
|
|
2 |
import subprocess
|
3 |
import cv2
|
4 |
|
5 |
-
# with subprocess and an extra argument '
|
6 |
# yt-dlp is instaled in .d4
|
7 |
# Download Part of Video
|
8 |
# yt-dlp https://www.youtube.com/watch?v=UZ9uyQI3pF0 --downloader ffmpeg --downloader-args "ffmpeg_i:-ss 997 -to 2512"
|
@@ -47,7 +47,7 @@ DESCRIPTIONS = [
|
|
47 |
'01_Schick_AII840_001.txt', # text
|
48 |
'statue in shire, hill river, vogels.', # audiocraft
|
49 |
'G. Schick, Bildnis der Heinrike Dannecker, 1802', # cv2 puttext title
|
50 |
-
'
|
51 |
],
|
52 |
# 2
|
53 |
[
|
@@ -69,7 +69,7 @@ DESCRIPTIONS = [
|
|
69 |
[
|
70 |
'04_Friedrich_FV317_001.jpg',
|
71 |
'04_Friedrich_FV317_001.txt',
|
72 |
-
'
|
73 |
'C. D. Friedrich, Der Watzmann, 1824',
|
74 |
'en_US/m-ailabs_low#mary_ann',
|
75 |
],
|
@@ -146,7 +146,7 @@ SILENT_VIDEO = '_silent_video.mp4'
|
|
146 |
# SILENT CLIP
|
147 |
|
148 |
|
149 |
-
for img, text,
|
150 |
|
151 |
|
152 |
|
@@ -185,7 +185,7 @@ for img, text, scene, title, voice in DESCRIPTIONS[2:4]:
|
|
185 |
"tts.py",
|
186 |
"--text", PIC_DIR + text,
|
187 |
'--image', '_tmp_banner.png',
|
188 |
-
'--
|
189 |
'--voice', voice,
|
190 |
'--out_file', OUT_FILE, # save to correct location is handled in client
|
191 |
])
|
|
|
2 |
import subprocess
|
3 |
import cv2
|
4 |
|
5 |
+
# with subprocess and an extra argument 'soundscape' and a 'resized image saved as png' we can call the server
|
6 |
# yt-dlp is instaled in .d4
|
7 |
# Download Part of Video
|
8 |
# yt-dlp https://www.youtube.com/watch?v=UZ9uyQI3pF0 --downloader ffmpeg --downloader-args "ffmpeg_i:-ss 997 -to 2512"
|
|
|
47 |
'01_Schick_AII840_001.txt', # text
|
48 |
'statue in shire, hill river, vogels.', # audiocraft
|
49 |
'G. Schick, Bildnis der Heinrike Dannecker, 1802', # cv2 puttext title
|
50 |
+
'en_US/vctk_low#p326', #'en_US/m-ailabs_low#judy_bieber', #'en_US/m-ailabs_low#mary_ann',
|
51 |
],
|
52 |
# 2
|
53 |
[
|
|
|
69 |
[
|
70 |
'04_Friedrich_FV317_001.jpg',
|
71 |
'04_Friedrich_FV317_001.txt',
|
72 |
+
'mountain wind',
|
73 |
'C. D. Friedrich, Der Watzmann, 1824',
|
74 |
'en_US/m-ailabs_low#mary_ann',
|
75 |
],
|
|
|
146 |
# SILENT CLIP
|
147 |
|
148 |
|
149 |
+
for img, text, soundscape, title, voice in DESCRIPTIONS[2:4]:
|
150 |
|
151 |
|
152 |
|
|
|
185 |
"tts.py",
|
186 |
"--text", PIC_DIR + text,
|
187 |
'--image', '_tmp_banner.png',
|
188 |
+
'--soundscape', soundscape,
|
189 |
'--voice', voice,
|
190 |
'--out_file', OUT_FILE, # save to correct location is handled in client
|
191 |
])
|