Spaces:
Running
Running
NeuroSenko
commited on
Commit
•
8f40c33
1
Parent(s):
da590b9
added install+start scripts; save audio into out_audio folder
Browse files- .gitignore +3 -0
- README.md +5 -1
- app.py +9 -2
- install.bat +3 -0
- out_audio/audio files will be placed here.txt +0 -0
- start.bat +2 -0
.gitignore
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
venv/
|
2 |
+
out_audio/*.wav
|
3 |
+
latest_silero_models.yml
|
README.md
CHANGED
@@ -9,4 +9,8 @@ app_file: app.py
|
|
9 |
pinned: false
|
10 |
---
|
11 |
|
12 |
-
|
|
|
|
|
|
|
|
|
|
9 |
pinned: false
|
10 |
---
|
11 |
|
12 |
+
How to run locally using Windows:
|
13 |
+
1. Mare sure you have installed ffmpeg in your system
|
14 |
+
2. Clone the repo: `git clone https://huggingface.co/spaces/NeuroSenko/tts-silero`
|
15 |
+
3. Run `install.bat`
|
16 |
+
4. Run `start.bat`
|
app.py
CHANGED
@@ -1,7 +1,9 @@
|
|
|
|
|
|
|
|
|
|
1 |
import gradio as gr
|
2 |
import torch
|
3 |
-
|
4 |
-
# from IPython.display import Audio, display
|
5 |
from omegaconf import OmegaConf
|
6 |
|
7 |
torch.hub.download_url_to_file(
|
@@ -55,8 +57,12 @@ def change_model(language, model_name):
|
|
55 |
|
56 |
|
57 |
def generate_audio_by_text(text, text_type, speaker):
|
|
|
|
|
|
|
58 |
if text_type == 'SSML':
|
59 |
return model.save_wav(
|
|
|
60 |
ssml_text=text,
|
61 |
speaker=speaker,
|
62 |
sample_rate=sample_rate,
|
@@ -65,6 +71,7 @@ def generate_audio_by_text(text, text_type, speaker):
|
|
65 |
)
|
66 |
else:
|
67 |
return model.save_wav(
|
|
|
68 |
text=text,
|
69 |
speaker=speaker,
|
70 |
sample_rate=sample_rate,
|
|
|
1 |
+
import os
|
2 |
+
from datetime import datetime
|
3 |
+
from inspect import signature
|
4 |
+
|
5 |
import gradio as gr
|
6 |
import torch
|
|
|
|
|
7 |
from omegaconf import OmegaConf
|
8 |
|
9 |
torch.hub.download_url_to_file(
|
|
|
57 |
|
58 |
|
59 |
def generate_audio_by_text(text, text_type, speaker):
|
60 |
+
output_file_name = "{datetime}.wav".format(datetime=datetime.now().isoformat().replace(':', '-'))
|
61 |
+
output = os.path.join("out_audio", output_file_name)
|
62 |
+
|
63 |
if text_type == 'SSML':
|
64 |
return model.save_wav(
|
65 |
+
audio_path=output,
|
66 |
ssml_text=text,
|
67 |
speaker=speaker,
|
68 |
sample_rate=sample_rate,
|
|
|
71 |
)
|
72 |
else:
|
73 |
return model.save_wav(
|
74 |
+
audio_path=output,
|
75 |
text=text,
|
76 |
speaker=speaker,
|
77 |
sample_rate=sample_rate,
|
install.bat
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
python -m venv ./venv
|
2 |
+
call .\venv\Scripts\activate.bat
|
3 |
+
pip install -r requirements.txt
|
out_audio/audio files will be placed here.txt
ADDED
File without changes
|
start.bat
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
call .\venv\Scripts\activate.bat
|
2 |
+
python app.py
|