numz commited on
Commit
32cb79e
1 Parent(s): cefc796

Mac user support

Browse files
Files changed (1) hide show
  1. README.md +35 -0
README.md CHANGED
@@ -83,6 +83,7 @@ It improves the quality of the lip-sync videos generated by the [Wav2Lip tool](h
83
 
84
  ## 💻 Installation
85
 
 
86
  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.
87
  ![Illustration](demo/visual_studio_1.png)
88
  ![Illustration](demo/visual_studio_2.png)
@@ -136,6 +137,40 @@ set each field and click "Agree and access repository"
136
  ```
137
  10. double click on wav2lip-studio.bat, that will install the requirements and download models
138
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
139
  ## Tutorial
140
  - [FR version](https://youtu.be/43Q8YASkcUA)
141
  - [EN Version](https://youtu.be/B84A5alpPDc)
 
83
 
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)
 
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
+ brew update
144
+ brew install python@3.9
145
+ brew install git-lfs
146
+ git-lfs install
147
+ `
148
+ 3. Install environnement and requirements
149
+ `
150
+ cd /YourWav2lipStudioFolder
151
+ /opt/homebrew/bin/python3.9 -m venv venv
152
+ ./venv/bin/python3.9 -m pip install torch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2
153
+ ./venv/bin/python3.9 -m pip install -r requirements.txt
154
+ ./venv/bin/python3.9 -m pip install transformers==4.33.2
155
+ ./venv/bin/python3.9 -m pip install numpy==1.24.4
156
+ `
157
+ if It doesn't works or too long on pip install -r requirements.txt
158
+ `
159
+ ./venv/bin/python3.9 -m pip install inaSpeechSegmenter
160
+ ./venv/bin/python3.9 -m pip install gradio==4.14.0 imutils==0.5.4 numpy opencv-python==4.8.0.76 scipy==1.11.2 requests==2.28.1 pillow==9.3.0 librosa==0.10.0 opencv-contrib-python==4.8.0.76 huggingface_hub==0.20.2 tqdm==4.66.1 cutlet==0.3.0 numba==0.57.1 imageio_ffmpeg==0.4.9 insightface==0.7.3 unidic==1.1.0 onnx==1.14.1 onnxruntime==1.16.0 psutil==5.9.5 lpips==0.1.4 GitPython==3.1.36 facexlib==0.3.0 gfpgan==1.3.8 gdown==4.7.1 pyannote.audio==3.1.1 TTS==0.21.2 openai-whisper==20231117 resampy==0.4.0 scenedetect==0.6.2 uvicorn==0.23.2 starlette==0.35.1 fastapi==0.109.0 fugashii
161
+ ./venv/bin/python3.9 -m pip install torch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2
162
+ ./venv/bin/python3.9 -m pip install transformers==4.33.2
163
+ ./venv/bin/python3.9 -m pip install numpy==1.24.4
164
+ `
165
+ 3. Install models
166
+ `
167
+ git clone https://huggingface.co/numz/wav2lip_studio models
168
+ `
169
+ 5. Launch UI
170
+ `
171
+ ./venv/bin/python3.9 wav2lip_studio.py
172
+ `
173
+
174
  ## Tutorial
175
  - [FR version](https://youtu.be/43Q8YASkcUA)
176
  - [EN Version](https://youtu.be/B84A5alpPDc)