Text-to-Audio
Audiocraft
English
audiogen
styletts2
shift-tts
sound
audio-generation
text-to-speech
mimic3
Instructions to use dkounadis/artificial-styletts2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Audiocraft
How to use dkounadis/artificial-styletts2 with Audiocraft:
from audiocraft.models import AudioGen model = AudioGen.get_pretrained("dkounadis/artificial-styletts2") model.set_generation_params(duration=5) # generate 5 seconds. descriptions = ['dog barking', 'sirene of an emergency vehicle', 'footsteps in a corridor'] wav = model.generate(descriptions) # generates 3 samples. - Notebooks
- Google Colab
- Kaggle
fixed last chapter saved no TTS in audiobook
Browse files- audiobook.py +4 -1
audiobook.py
CHANGED
|
@@ -54,8 +54,11 @@ for vox in voices:
|
|
| 54 |
|
| 55 |
total = []
|
| 56 |
chapter = []
|
|
|
|
|
|
|
|
|
|
| 57 |
|
| 58 |
-
for para in d.paragraphs
|
| 59 |
t = para.text
|
| 60 |
|
| 61 |
|
|
|
|
| 54 |
|
| 55 |
total = []
|
| 56 |
chapter = []
|
| 57 |
+
|
| 58 |
+
final_paragraph_for_saving_last_chapter = d.paragraphs[-1]
|
| 59 |
+
final_paragraph_for_saving_last_chapter.text = 'CHAPTER:'
|
| 60 |
|
| 61 |
+
for para in d.paragraphs + [final_paragraph_for_saving_last_chapter,]: # final paragraph is only to go into if & save .wav of last CHAPTER
|
| 62 |
t = para.text
|
| 63 |
|
| 64 |
|