Update README.md
Browse files
README.md
CHANGED
@@ -84,6 +84,7 @@ It improves the quality of the lip-sync videos generated by the [Wav2Lip tool](h
|
|
84 |
## 💻 Installation
|
85 |
|
86 |
# Windows Users
|
|
|
87 |
1.Install [Visual Studio](https://visualstudio.microsoft.com/fr/downloads/). During the install, make sure to include the Python and C++ packages in visual studio installer.
|
88 |
![Illustration](demo/visual_studio_1.png)
|
89 |
![Illustration](demo/visual_studio_2.png)
|
@@ -116,28 +117,10 @@ It improves the quality of the lip-sync videos generated by the [Wav2Lip tool](h
|
|
116 |
```bash
|
117 |
set PYTHON="your python.exe path"
|
118 |
```
|
119 |
-
8.
|
120 |
-
To do so, go to both link:
|
121 |
-
- [pyannote diarization-3.1 huggingface repository](https://huggingface.co/pyannote/speaker-diarization-3.1)
|
122 |
-
- [pyannote segmentation-3.0 huggingface repository](https://huggingface.co/pyannote/segmentation-3.0)
|
123 |
-
|
124 |
-
set each field and click "Agree and access repository"
|
125 |
-
![Illustration](demo/hf_aggrement.png)
|
126 |
-
|
127 |
-
9. Create an access token to Huggingface:
|
128 |
-
1. Connect with your account
|
129 |
-
2. go to [access tokens](https://huggingface.co/settings/token) in settings
|
130 |
-
3. create a new token in read mode
|
131 |
-
4. copy the token
|
132 |
-
5. paste it in the file api_keys.json
|
133 |
-
```json
|
134 |
-
{
|
135 |
-
"huggingface_token": "your token"
|
136 |
-
}
|
137 |
-
```
|
138 |
-
10. double click on wav2lip-studio.bat, that will install the requirements and download models
|
139 |
|
140 |
# MACOS Users
|
|
|
141 |
1. Install python 3.9
|
142 |
|
143 |
`
|
@@ -176,6 +159,28 @@ set each field and click "Agree and access repository"
|
|
176 |
./venv/bin/python3.9 wav2lip_studio.py
|
177 |
`
|
178 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
179 |
## Tutorial
|
180 |
- [FR version](https://youtu.be/43Q8YASkcUA)
|
181 |
- [EN Version](https://youtu.be/B84A5alpPDc)
|
|
|
84 |
## 💻 Installation
|
85 |
|
86 |
# Windows Users
|
87 |
+
|
88 |
1.Install [Visual Studio](https://visualstudio.microsoft.com/fr/downloads/). During the install, make sure to include the Python and C++ packages in visual studio installer.
|
89 |
![Illustration](demo/visual_studio_1.png)
|
90 |
![Illustration](demo/visual_studio_2.png)
|
|
|
117 |
```bash
|
118 |
set PYTHON="your python.exe path"
|
119 |
```
|
120 |
+
8. double click on wav2lip-studio.bat, that will install the requirements and download models
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
121 |
|
122 |
# MACOS Users
|
123 |
+
|
124 |
1. Install python 3.9
|
125 |
|
126 |
`
|
|
|
159 |
./venv/bin/python3.9 wav2lip_studio.py
|
160 |
`
|
161 |
|
162 |
+
# All Users
|
163 |
+
|
164 |
+
1. pyannote.audio:You need to agree to share your contact information to access pyannote models.
|
165 |
+
To do so, go to both link:
|
166 |
+
- [pyannote diarization-3.1 huggingface repository](https://huggingface.co/pyannote/speaker-diarization-3.1)
|
167 |
+
- [pyannote segmentation-3.0 huggingface repository](https://huggingface.co/pyannote/segmentation-3.0)
|
168 |
+
|
169 |
+
set each field and click "Agree and access repository"
|
170 |
+
![Illustration](demo/hf_aggrement.png)
|
171 |
+
|
172 |
+
2. Create an access token to Huggingface:
|
173 |
+
1. Connect with your account
|
174 |
+
2. go to [access tokens](https://huggingface.co/settings/token) in settings
|
175 |
+
3. create a new token in read mode
|
176 |
+
4. copy the token
|
177 |
+
5. paste it in the file api_keys.json
|
178 |
+
```json
|
179 |
+
{
|
180 |
+
"huggingface_token": "your token"
|
181 |
+
}
|
182 |
+
```
|
183 |
+
|
184 |
## Tutorial
|
185 |
- [FR version](https://youtu.be/43Q8YASkcUA)
|
186 |
- [EN Version](https://youtu.be/B84A5alpPDc)
|