Dionyssos commited on
Commit
2a2d5c1
1 Parent(s): faf666f

thumbs/links

Browse files
README.md CHANGED
@@ -19,12 +19,12 @@ tags:
19
  ---
20
 
21
 
22
- # Affective TTS / SoundScape
23
 
24
- - [SHIFT TTS tool](https://github.com/audeering/shift) with [Affective voices](https://audeering.github.io/shift/)
25
  - Analysis of emotionality [#1](https://huggingface.co/dkounadis/artificial-styletts2/discussions/2)
26
  - Soundscape `e.g. trees, water, hills,`, generation via [AudioGen](https://huggingface.co/dkounadis/artificial-styletts2/discussions/3)
27
- - `landscape2soundscape.py` shows how to overlay TTS & Soundscape to Images and create videos
28
 
29
  ## Available Voices
30
 
@@ -32,8 +32,6 @@ tags:
32
 
33
  ## API
34
 
35
- Install
36
-
37
  ```
38
  virtualenv --python=python3 ~/.envs/.my_env
39
  source ~/.envs/.my_env/bin/activate
@@ -47,34 +45,7 @@ Flask
47
  CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=./hf_home CUDA_VISIBLE_DEVICES=2 python api.py
48
  ```
49
 
50
- The following need `api.py` to be running on a `tmux session`.
51
-
52
- ## Text 2 Speech
53
-
54
- ```python
55
- # Basic TTS - See Available Voices
56
- python tts.py --text sample.txt --voice "en_US/m-ailabs_low#mary_ann" --affective
57
-
58
- # voice cloning
59
- python tts.py --text sample.txt --native assets/native_voice.wav
60
- ```
61
-
62
- ## Image 2 Video
63
-
64
- ```python
65
- # Make video narrating an image - All above TTS args apply also here!
66
- python tts.py --text sample.txt --image assets/image_from_T31.jpg
67
- ```
68
-
69
- ## Video 2 Video
70
-
71
- ```python
72
- # Video Dubbing - from time-stamped subtitles (.srt)
73
- python tts.py --text assets/head_of_fortuna_en.srt --video assets/head_of_fortuna.mp4
74
-
75
- # Video narration - from text description (.txt)
76
- python tts.py --text assets/head_of_fortuna_GPT.txt --video assets/head_of_fortuna.mp4
77
- ```
78
 
79
  ## Landscape 2 Soundscape
80
 
@@ -83,7 +54,7 @@ python tts.py --text assets/head_of_fortuna_GPT.txt --video assets/head_of_fortu
83
  python landscape2soundscape.py
84
  ```
85
 
86
- # Examples
87
 
88
  Substitute Native voice via TTS
89
 
@@ -132,9 +103,9 @@ python tts.py --text sample.txt --image assets/image_from_T31.jpg
132
  ```
133
 
134
  ## Landscape 2 Soundscape
135
- - YouTube Videos
 
136
 
137
- [![01schic](uc_spk_Landscape2Soundscape_Masterpieces_pics/01_Schick_AII840_001.jpg)](https://www.youtube.com/watch?v=FCYS29OrA1s)
138
 
139
 
140
 
@@ -143,6 +114,10 @@ python tts.py --text sample.txt --image assets/image_from_T31.jpg
143
  python landscape2soundscape.py
144
  ```
145
 
 
 
 
 
146
 
147
  # Live Demo - Paplay
148
 
 
19
  ---
20
 
21
 
22
+ # Affective TTS / SoundScapes
23
 
24
+ - [SHIFT TTS tool](https://github.com/audeering/shift)
25
  - Analysis of emotionality [#1](https://huggingface.co/dkounadis/artificial-styletts2/discussions/2)
26
  - Soundscape `e.g. trees, water, hills,`, generation via [AudioGen](https://huggingface.co/dkounadis/artificial-styletts2/discussions/3)
27
+ - `landscape2soundscape.py` shows how to overlay TTS & sound to image and create video
28
 
29
  ## Available Voices
30
 
 
32
 
33
  ## API
34
 
 
 
35
  ```
36
  virtualenv --python=python3 ~/.envs/.my_env
37
  source ~/.envs/.my_env/bin/activate
 
45
  CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=./hf_home CUDA_VISIBLE_DEVICES=2 python api.py
46
  ```
47
 
48
+ The following need `api.py` to be already running `on a tmux session`.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
 
50
  ## Landscape 2 Soundscape
51
 
 
54
  python landscape2soundscape.py
55
  ```
56
 
57
+ # YouTube Videos / Examples
58
 
59
  Substitute Native voice via TTS
60
 
 
103
  ```
104
 
105
  ## Landscape 2 Soundscape
106
+ - YouTube Videos For SHIFT demo / Collaboration with [SMB](https://www.smb.museum/home/)
107
+
108
 
 
109
 
110
 
111
 
 
114
  python landscape2soundscape.py
115
  ```
116
 
117
+ [![01](uc_spk_Landscape2Soundscape_Masterpieces_pics/thumb____01_Schick_AII840_001.jpg)](https://youtu.be/SSi3gUO4GtY)
118
+
119
+ [![02](uc_spk_Landscape2Soundscape_Masterpieces_pics/thumb____02_Constable_AI555_001.jpg)(https://youtu.be/2YjxAPkdXIc)
120
+
121
 
122
  # Live Demo - Paplay
123
 
landscape2soundscape.py CHANGED
@@ -110,7 +110,7 @@ DESCRIPTIONS = [
110
  '09_Blechen_AII823_001.jpg',
111
  '09_Blechen_AII823_001.txt',
112
  'Cascade in Africa',
113
- 'C. Blechen, Wasserfälle Bei Tivoli, 1832',
114
  'en_US/m-ailabs_low#mary_ann',
115
  ],
116
  # 10
@@ -118,7 +118,7 @@ DESCRIPTIONS = [
118
  '10_Boecklin_967648_NG2-80_001_rsz.jpg',
119
  '10_Boecklin_967648_NG2-80_001.txt',
120
  'Hades ades at it sisland',
121
- 'A. Böcklin, Toteninsel, 1883',
122
  'en_US/cmu-arctic_low#jmk',
123
  ],
124
  # 11
@@ -175,6 +175,8 @@ for img, text, scene, title, voice in DESCRIPTIONS[:20]:
175
  im[offset_h:h+offset_h, :w, :] = (.4 * im[offset_h:h+offset_h, :w, :] + .6 * fram).astype(np.uint8)
176
 
177
  cv2.imwrite('_tmp_banner.png', im)
 
 
178
  OUT_FILE = img.split('/')[-1].replace('.','__') + '.mp4' # assets / -1
179
  print(f'{OUT_FILE=}\n')
180
  subprocess.run(
 
110
  '09_Blechen_AII823_001.jpg',
111
  '09_Blechen_AII823_001.txt',
112
  'Cascade in Africa',
113
+ 'C. Blechen, Wasserfalle Bei Tivoli, 1832',
114
  'en_US/m-ailabs_low#mary_ann',
115
  ],
116
  # 10
 
118
  '10_Boecklin_967648_NG2-80_001_rsz.jpg',
119
  '10_Boecklin_967648_NG2-80_001.txt',
120
  'Hades ades at it sisland',
121
+ 'A. Bocklin, Toteninsel, 1883',
122
  'en_US/cmu-arctic_low#jmk',
123
  ],
124
  # 11
 
175
  im[offset_h:h+offset_h, :w, :] = (.4 * im[offset_h:h+offset_h, :w, :] + .6 * fram).astype(np.uint8)
176
 
177
  cv2.imwrite('_tmp_banner.png', im)
178
+ print('save 2nd',PIC_DIR + 'thumb____' + img)
179
+ cv2.imwrite(PIC_DIR + 'thumb____' + img, cv2.resize(im, (im.shape[1]//4, im.shape[0]//4)))
180
  OUT_FILE = img.split('/')[-1].replace('.','__') + '.mp4' # assets / -1
181
  print(f'{OUT_FILE=}\n')
182
  subprocess.run(
uc_spk_Landscape2Soundscape_Masterpieces_pics/thumb____01_Schick_AII840_001.jpg ADDED
uc_spk_Landscape2Soundscape_Masterpieces_pics/thumb____02_Constable_AI555_001.jpg ADDED