Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,95 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
license: openrail
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
library_name: TTS
|
3 |
+
task: text-to-speech
|
4 |
+
tags:
|
5 |
+
- Persian
|
6 |
+
- TTS
|
7 |
+
- Farsi
|
8 |
+
- Coqui
|
9 |
+
- CoquiTTS
|
10 |
+
- pytorch
|
11 |
+
- audio
|
12 |
+
- text-to-speech
|
13 |
+
language: fa
|
14 |
+
datasets:
|
15 |
+
- persian-tts-dataset
|
16 |
+
widget:
|
17 |
+
- text: .زندگی فقط یک بار است؛ از آن به خوبی استفاده کن
|
18 |
+
example_title: Hello, this is a test run.
|
19 |
license: openrail
|
20 |
+
pipeline_tag: text-to-speech
|
21 |
---
|
22 |
+
|
23 |
+
# **persian-tts-female-vits**
|
24 |
+
|
25 |
+
- persian-tts-female vits model for text to speech purposes.
|
26 |
+
- Persian فارسی
|
27 |
+
- Single-speaker female voice
|
28 |
+
- Trained on <span style="color: #0072ff;font-weight: bold;">[persian-tts-dataset-male](https://www.kaggle.com/datasets/magnoliasis/persian-tts-dataset-famale)</span> dataset
|
29 |
+
- [GitHub Repo](https://github.com/coqui-ai/TTS)
|
30 |
+
- <span style="color: #0072ff;font-weight: bold;">[Demo](https://huggingface.co/spaces/Kamtera/Persian-tts-CoquiTTS)</span>
|
31 |
+
|
32 |
+
|
33 |
+
# **Uses**
|
34 |
+
|
35 |
+
Install dependencies:
|
36 |
+
```python
|
37 |
+
!pip install TTS
|
38 |
+
!sudo apt-get -y install espeak-ng
|
39 |
+
```
|
40 |
+
|
41 |
+
Generate audio from text:
|
42 |
+
|
43 |
+
##### using cli:
|
44 |
+
```python
|
45 |
+
!tts --text "زندگی فقط یک بار است؛ از آن به خوبی استفاده کن" \
|
46 |
+
--model_path ".pth" \
|
47 |
+
--config_path "config.json" \
|
48 |
+
--out_path "speech1.wav"
|
49 |
+
```
|
50 |
+
##### python api:
|
51 |
+
|
52 |
+
```python
|
53 |
+
|
54 |
+
from TTS.config import load_config
|
55 |
+
from TTS.utils.manage import ModelManager
|
56 |
+
from TTS.utils.synthesizer import Synthesizer
|
57 |
+
|
58 |
+
config="config.json"
|
59 |
+
model="best_model_30824.pth"
|
60 |
+
|
61 |
+
model_path =model # Absolute path to the model checkpoint.pth
|
62 |
+
config_path =config # Absolute path to the model config.json
|
63 |
+
|
64 |
+
text=".زندگی فقط یک بار است؛ از آن به خوبی استفاده کن"
|
65 |
+
|
66 |
+
synthesizer = Synthesizer(
|
67 |
+
model_path, config_path
|
68 |
+
)
|
69 |
+
wavs = synthesizer.tts(text)
|
70 |
+
synthesizer.save_wav(wavs, 'sp.wav')
|
71 |
+
```
|
72 |
+
Display audio:
|
73 |
+
|
74 |
+
|
75 |
+
```python
|
76 |
+
import IPython
|
77 |
+
IPython.display.Audio('sp.wav')
|
78 |
+
```
|
79 |
+
|
80 |
+
|
81 |
+
- **Hours used:** 10
|
82 |
+
- **Cloud Provider:** kaggle
|
83 |
+
|
84 |
+
|
85 |
+
|
86 |
+
# How to Get Started with the Model
|
87 |
+
|
88 |
+
Use the code below to get started with the model.
|
89 |
+
|
90 |
+
<details>
|
91 |
+
<summary> Click to expand </summary>
|
92 |
+
|
93 |
+
More information needed
|
94 |
+
|
95 |
+
</details>
|