numz commited on
Commit
2f442f0
1 Parent(s): 36df9b9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -8
README.md CHANGED
@@ -85,30 +85,41 @@ It improves the quality of the lip-sync videos generated by the [Wav2Lip tool](h
85
 
86
  1. Install [python 3.10.11](https://www.python.org/downloads/release/python-31011/)
87
  2. Install [git](https://git-scm.com/downloads)
88
- 3. Check python and git installation
 
 
89
  ```bash
90
  python --version
91
  git --version
 
92
  ```
93
  Must return something like
94
  ```bash
95
  Python 3.10.11
96
  git version 2.35.1.windows.2
 
 
 
 
 
97
  ```
98
- 4. 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.
99
  ![Illustration](demo/visual_studio_1.png)
100
  ![Illustration](demo/visual_studio_2.png)
101
- 5. if you have multiple Python version on your computer edit wav2lip-studio.bat and change the following line:
102
  ```bash
103
  REM set PYTHON="your python.exe path"
104
  ```
105
- ```bash
106
  set PYTHON="your python.exe path"
107
  ```
108
- 6. pyannote.audio:You need to agree to share your contact information to access pyannote models.
109
- To do so, go to [pyannote diarization-3.1 huggingface repository](https://huggingface.co/pyannote/speaker-diarization-3.1) AND [pyannote segmentation-3.0 huggingface repository](https://huggingface.co/pyannote/segmentation-3.0) set each field and click "Agree and access repository"
 
 
 
110
  ![Illustration](demo/hf_aggrement.png)
111
- 7. Create an access token to Huggingface:
112
  1. Connect with your account
113
  2. go to [access tokens](https://huggingface.co/settings/token) in settings
114
  3. create a new token in read mode
@@ -119,7 +130,7 @@ To do so, go to [pyannote diarization-3.1 huggingface repository](https://huggin
119
  "huggingface_token": "your token"
120
  }
121
  ```
122
- 8. double click on wav2lip-studio.bat, that will install the requirements and download the models
123
 
124
  ## Tutorial
125
  - [FR version](https://youtu.be/43Q8YASkcUA)
 
85
 
86
  1. Install [python 3.10.11](https://www.python.org/downloads/release/python-31011/)
87
  2. Install [git](https://git-scm.com/downloads)
88
+ 3. Install [Cuda 11.8](https://developer.nvidia.com/cuda-11-8-0-download-archive) if not ever done.
89
+ ![Illustration](demo/cuda.png)
90
+ 4. Check python and git installation
91
  ```bash
92
  python --version
93
  git --version
94
+ nvcc --version
95
  ```
96
  Must return something like
97
  ```bash
98
  Python 3.10.11
99
  git version 2.35.1.windows.2
100
+ nvcc: NVIDIA (R) Cuda compiler driver
101
+ Copyright (c) 2005-2022 NVIDIA Corporation
102
+ Built on Wed_Sep_21_10:41:10_Pacific_Daylight_Time_2022
103
+ Cuda compilation tools, release 11.8, V11.8.89
104
+ Build cuda_11.8.r11.8/compiler.31833905_0
105
  ```
106
+ 5. 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.
107
  ![Illustration](demo/visual_studio_1.png)
108
  ![Illustration](demo/visual_studio_2.png)
109
+ 6. if you have multiple Python version on your computer edit wav2lip-studio.bat and change the following line:
110
  ```bash
111
  REM set PYTHON="your python.exe path"
112
  ```
113
+ ```bash
114
  set PYTHON="your python.exe path"
115
  ```
116
+ 7. pyannote.audio:You need to agree to share your contact information to access pyannote models.
117
+ To do so, go to :
118
+ - [pyannote diarization-3.1 huggingface repository](https://huggingface.co/pyannote/speaker-diarization-3.1)
119
+ - [pyannote segmentation-3.0 huggingface repository](https://huggingface.co/pyannote/segmentation-3.0)
120
+ set each field and click "Agree and access repository"
121
  ![Illustration](demo/hf_aggrement.png)
122
+ 9. Create an access token to Huggingface:
123
  1. Connect with your account
124
  2. go to [access tokens](https://huggingface.co/settings/token) in settings
125
  3. create a new token in read mode
 
130
  "huggingface_token": "your token"
131
  }
132
  ```
133
+ 10. double click on wav2lip-studio.bat, that will install the requirements and download models
134
 
135
  ## Tutorial
136
  - [FR version](https://youtu.be/43Q8YASkcUA)