Update README.md
Browse files
README.md
CHANGED
@@ -1,127 +1,7 @@
|
|
1 |
-
# Kokoro-TTS
|
2 |
-
|
3 |
-
**Note:** This is not the official repository. Alternatives [kokoro-onnx](https://github.com/thewh1teagle/kokoro-onnx), [Kokoro-FastAPI](https://github.com/remsky/Kokoro-FastAPI), [kokoro](https://github.com/hexgrad/kokoro), [kokoro-web](https://huggingface.co/spaces/webml-community/kokoro-web), [Kokoro-Custom-Voice](https://huggingface.co/spaces/ysharma/Make_Custom_Voices_With_KokoroTTS)
|
4 |
-
|
5 |
-
[](https://colab.research.google.com/github/NeuralFalconYT/Kokoro-82M-WebUI/blob/main/Kokoro_82M_Colab.ipynb) <br>
|
6 |
-
[](https://huggingface.co/spaces/hexgrad/Kokoro-TTS)
|
7 |
-
|
8 |
-
|
9 |
---
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
```bash
|
17 |
-
git clone https://github.com/NeuralFalconYT/Kokoro-82M-WebUI.git
|
18 |
-
cd Kokoro-82M-WebUI
|
19 |
-
```
|
20 |
-
|
21 |
-
#### 2. Create a Python Virtual Environment:
|
22 |
-
```bash
|
23 |
-
python -m venv myenv
|
24 |
-
```
|
25 |
-
This command creates a new Python virtual environment named `myenv` for isolating dependencies.
|
26 |
-
|
27 |
-
#### 3. Activate the Virtual Environment:
|
28 |
-
- **For Windows:**
|
29 |
-
```bash
|
30 |
-
myenv\Scripts\activate
|
31 |
-
```
|
32 |
-
- **For Linux:**
|
33 |
-
```bash
|
34 |
-
source myenv/bin/activate
|
35 |
-
```
|
36 |
-
This activates the virtual environment, enabling you to install and run dependencies in an isolated environment.
|
37 |
-
Here’s the corrected version of point 4, with proper indentation for the subpoints:
|
38 |
-
|
39 |
-
|
40 |
-
#### 4. Install PyTorch:
|
41 |
-
|
42 |
-
- **For GPU (CUDA-enabled installation):**
|
43 |
-
- Check CUDA Version (for GPU setup):
|
44 |
-
```bash
|
45 |
-
nvcc --version
|
46 |
-
```
|
47 |
-
Find your CUDA version example ```11.8```
|
48 |
-
|
49 |
-
- Visit [PyTorch Get Started](https://pytorch.org/get-started/locally/) and install the version compatible with your CUDA setup.:<br>
|
50 |
-
- For CUDA 11.8:
|
51 |
-
```
|
52 |
-
pip install torch --index-url https://download.pytorch.org/whl/cu118
|
53 |
-
```
|
54 |
-
- For CUDA 12.1:
|
55 |
-
```
|
56 |
-
pip install torch --index-url https://download.pytorch.org/whl/cu121
|
57 |
-
```
|
58 |
-
- For CUDA 12.4:
|
59 |
-
```
|
60 |
-
pip install torch --index-url https://download.pytorch.org/whl/cu124
|
61 |
-
```
|
62 |
-
- **For CPU (if not using GPU):**
|
63 |
-
```bash
|
64 |
-
pip install torch
|
65 |
-
```
|
66 |
-
This installs the CPU-only version of PyTorch.
|
67 |
-
|
68 |
-
|
69 |
-
#### 5. Install Required Dependencies:
|
70 |
-
```bash
|
71 |
-
pip install -r requirements.txt
|
72 |
-
```
|
73 |
-
This installs all the required Python libraries listed in the `requirements.txt` file.
|
74 |
-
|
75 |
-
#### 6. Download Model and Get Latest VoicePack:
|
76 |
-
```bash
|
77 |
-
python download_model.py
|
78 |
-
```
|
79 |
-
|
80 |
-
---
|
81 |
-
|
82 |
-
#### 7. Install eSpeak NG
|
83 |
-
|
84 |
-
- **For Windows:**
|
85 |
-
1. Download the latest eSpeak NG release from the [eSpeak NG GitHub Releases](https://github.com/espeak-ng/espeak-ng/releases/tag/1.51).
|
86 |
-
2. Locate and download the file named **`espeak-ng-X64.msi`**.
|
87 |
-
3. Run the installer and follow the installation steps. Ensure that you install eSpeak NG in the default directory:
|
88 |
-
```
|
89 |
-
C:\Program Files\eSpeak NG
|
90 |
-
```
|
91 |
-
> **Note:** This default path is required for the application to locate eSpeak NG properly.
|
92 |
-
|
93 |
-
- **For Linux:**
|
94 |
-
1. Open your terminal.
|
95 |
-
2. Install eSpeak NG using the following command:
|
96 |
-
```bash
|
97 |
-
sudo apt-get -qq -y install espeak-ng > /dev/null 2>&1
|
98 |
-
```
|
99 |
-
> **Note:** This command suppresses unnecessary output for a cleaner installation process.
|
100 |
-
|
101 |
-
---
|
102 |
-
|
103 |
-
#### 8. Run Gradio App
|
104 |
-
|
105 |
-
To run the Gradio app, follow these steps:
|
106 |
-
|
107 |
-
1. **Activate the Virtual Environment:**
|
108 |
-
```bash
|
109 |
-
myenv\Scripts\activate
|
110 |
-
```
|
111 |
-
|
112 |
-
2. **Run the Application:**
|
113 |
-
```bash
|
114 |
-
python app.py
|
115 |
-
```
|
116 |
-
|
117 |
-
Alternatively, on Windows, double-click on `run_app.bat` to start the application.
|
118 |
-
|
119 |
-
---
|
120 |
-
|
121 |
-

|
122 |
-

|
123 |
-

|
124 |
-
|
125 |
-
### Credits
|
126 |
-
[Kokoro HuggingFace](https://huggingface.co/hexgrad/Kokoro-82M)
|
127 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: mit
|
3 |
+
title: Kokoro TTS
|
4 |
+
sdk: gradio
|
5 |
+
emoji: ⚡
|
6 |
+
short_description: Kokoro TTS WebUI
|
7 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|