Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

关于GPT-SoVITS和XTTS,README写的太简单了 #14

Closed
szdengdi opened this issue Feb 9, 2024 · 1 comment
Closed

关于GPT-SoVITS和XTTS,README写的太简单了 #14

szdengdi opened this issue Feb 9, 2024 · 1 comment
Labels
documentation Improvements or additions to documentation

Comments

@szdengdi
Copy link

szdengdi commented Feb 9, 2024

GPT-SoVITS和XTTS的配置写的太简单了。
GPT-SoVITS还有一堆包需要下载,还有nltk需要下载配置。
XTTS也是报:没有examples/female.wav、 tts_models--multilingual--multi-dataset--xtts_v2/config.json等错误。

README能否写详细点,或者类似Sadtalker,把调用的模型和存放位置都写一下。

@Kedreamix
Copy link
Owner

其实一开始是想着为了尊重原作者,有些东西可能没有说很多,最近会补充写的详细一点
如果安装对应的GPT-SoVITS环境可以进行 pip install -r VITS/requirements_gptsovits.txt
如果安装对应的XTTS环境可以进行pip install -r VITS/requirements_xtts.txt
对应的example我会放上去,有一些模型可能需要自动进行下载,模型应该可以下载

存放位置在最后有一个文件夹结构来着,是存在的,以及已经在huggingface搭建一个存放权重的仓库,到时候一个会更加清晰一点,也可以先看看https://huggingface.co/Kedreamix/Linly-Talker

Linly-Talker/ 
├── app.py
├── app_img.py
├── utils.py
├── Linly-api.py
├── Linly-api-fast.py
├── Linly-example.ipynb
├── README.md
├── README_zh.md
├── request-Linly-api.py
├── requirements_app.txt
├── scripts
│   └── download_models.sh
├──	src
│   ├── audio2exp_models
│   ├── audio2pose_models
│   ├── config
│   ├── cost_time.py
│   ├── face3d
│   ├── facerender
│   ├── generate_batch.py
│   ├── generate_facerender_batch.py
│   ├── Record.py
│   ├── test_audio2coeff.py
│   └── utils
├── inputs
│   ├── example.png
│   └── first_frame_dir
│       ├── example_landmarks.txt
│       ├── example.mat
│       └── example.png
├── examples
│   └── source_image
│       ├── art_0.png
│       ├── ......
│       └── sad.png
├── TFG
│   ├── __init__.py
│   ├── Wav2Lip.py
│   └── SadTalker.py
└── TTS
│   ├── __init__.py
│   ├── EdgeTTS.py
│   └── TTS_app.py
├── ASR
│   ├── __init__.py
│   ├── FunASR.py
│   └── Whisper.py
├── LLM
│   ├── __init__.py
│   ├── Gemini.py
│   ├── Linly.py
│   └── Qwen.py
....... // 以下是需要下载的权重路径(可选)
├── checkpoints // SadTalker 权重路径
│   ├── mapping_00109-model.pth.tar
│   ├── mapping_00229-model.pth.tar
│   ├── SadTalker_V0.0.2_256.safetensors
│   └── SadTalker_V0.0.2_512.safetensors
│   ├── lipsync_expert.pth
│   ├── visual_quality_disc.pth
│   ├── wav2lip_gan.pth
│   └── wav2lip.pth // Wav2Lip 权重陆军
├── gfpgan // GFPGAN 权重路径
│   └── weights
│       ├── alignment_WFLW_4HG.pth
│       └── detection_Resnet50_Final.pth
├── Linly-AI // Linly 权重路径
│   └── Chinese-LLaMA-2-7B-hf 
│       ├── config.json
│       ├── generation_config.json
│       ├── pytorch_model-00001-of-00002.bin
│       ├── pytorch_model-00002-of-00002.bin
│       ├── pytorch_model.bin.index.json
│       ├── README.md
│       ├── special_tokens_map.json
│       ├── tokenizer_config.json
│       └── tokenizer.model
├── Qwen // Qwen 权重路径
│   └── Qwen-1_8B-Chat
│       ├── cache_autogptq_cuda_256.cpp
│       ├── cache_autogptq_cuda_kernel_256.cu
│       ├── config.json
│       ├── configuration_qwen.py
│       ├── cpp_kernels.py
│       ├── examples
│       │   └── react_prompt.md
│       ├── generation_config.json
│       ├── LICENSE
│       ├── model-00001-of-00002.safetensors
│       ├── model-00002-of-00002.safetensors
│       ├── modeling_qwen.py
│       ├── model.safetensors.index.json
│       ├── NOTICE
│       ├── qwen_generation_utils.py
│       ├── qwen.tiktoken
│       ├── README.md
│       ├── tokenization_qwen.py
│       └── tokenizer_config.json

@Kedreamix Kedreamix added documentation Improvements or additions to documentation and removed In follow-up labels Mar 22, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation Improvements or additions to documentation
Projects
None yet
Development

No branches or pull requests

2 participants