blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2025-04-06 03:57:44 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #16 from AlexZhou1995/main

Browse Source 
Add install.sh & Fix requirement
This commit is contained in:
RVC-Boss 2024-01-17 15:51:25 +08:00 committed by GitHub
commit c912d75014
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 29 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
README.md
View File

@ -38,13 +38,21 @@ https://github.com/RVC-Boss/GPT-SoVITS/assets/129054828/05bee1fa-bdd8-4d85-9350-
Tested with Python 3.9, PyTorch 2.0.1, and CUDA 11. Tested with Python 3.9, PyTorch 2.0.1, and CUDA 11.
### Pip Packages ### Quick Install with Conda
```bash ```bash
pip install torch numpy scipy tensorboard librosa==0.9.2 numba==0.56.4 pytorch-lightning gradio==3.14.0 ffmpeg-python onnxruntime tqdm==4.59.0 cn2an pypinyin pyopenjtalk g2p_en conda create -n GPTSoVits python=3.9
conda activate GPTSoVits
bash install.sh
```
### Install Manually
#### Pip Packages
```bash
pip install torch numpy scipy tensorboard librosa==0.9.2 numba==0.56.4 pytorch-lightning gradio==3.14.0 ffmpeg-python onnxruntime tqdm cn2an pypinyin pyopenjtalk g2p_en chardet
``` ```
### Additional Requirements #### Additional Requirements
If you need Chinese ASR (supported by FunASR), install: If you need Chinese ASR (supported by FunASR), install:
@ -52,9 +60,14 @@ If you need Chinese ASR (supported by FunASR), install:
pip install modelscope torchaudio sentencepiece funasr pip install modelscope torchaudio sentencepiece funasr
``` ```
### FFmpeg #### FFmpeg
#### Ubuntu/Debian Users ##### Conda Users
```bash
conda install ffmpeg
```
##### Ubuntu/Debian Users
```bash ```bash
sudo apt install ffmpeg sudo apt install ffmpeg
@ -62,13 +75,13 @@ sudo apt install libsox-dev
conda install -c conda-forge 'ffmpeg<7' conda install -c conda-forge 'ffmpeg<7'
``` ```
#### MacOS Users ##### MacOS Users
```bash ```bash
brew install ffmpeg brew install ffmpeg
``` ```
#### Windows Users ##### Windows Users
Download and place [ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe) and [ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe) in the GPT-SoVITS root. Download and place [ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe) and [ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe) in the GPT-SoVITS root.

6
install.sh Normal file
View File

@ -0,0 +1,6 @@
#!/bin/bash
conda install -c conda-forge gcc
conda install -c conda-forge gxx
conda install ffmpeg cmake
conda install pytorch==2.1.1 torchvision==0.16.1 torchaudio==2.1.1 pytorch-cuda=11.8 -c pytorch -c nvidia
pip install -r requirements.txt

3
requirements.txt
View File

@ -7,7 +7,7 @@ pytorch-lightning
gradio==3.14.0 gradio==3.14.0
ffmpeg-python ffmpeg-python
onnxruntime onnxruntime
tqdm==4.59.0 tqdm
funasr funasr
cn2an cn2an
pypinyin pypinyin
@ -17,4 +17,5 @@ torchaudio
modelscope modelscope
sentencepiece sentencepiece
transformers transformers
chardet
PyYAML PyYAML