diff --git a/README.md b/README.md index 259cb27..891dc3e 100644 --- a/README.md +++ b/README.md @@ -9,13 +9,13 @@ Welcome to play around with the base model, a Trilingual Anime VITS! ### Currently Supported Tasks: - [x] Convert user's voice to characters listed [here](https://github.com/SongtingLiu/VITS_voice_conversion/blob/main/configs/finetune_speaker.json) - [x] Chinese, English, Japanese TTS with user's voice -- [ ] Chinese, English, Japanese TTS with custom characters... +- [x] Chinese, English, Japanese TTS with custom characters! ### Currently Supported Characters for TTS & VC: -- [x] Umamusume Pretty Derby -- [x] Sanoba Witch -- [x] Genshin Impact -- [ ] Custom characters... +- [x] Umamusume Pretty Derby (Used as base model pretraining) +- [x] Sanoba Witch (Used as base model pretraining) +- [x] Genshin Impact (Used as base model pretraining) +- [x] Any character you wish as long as you have their voices! @@ -24,22 +24,46 @@ Welcome to play around with the base model, a Trilingual Anime VITS! It's recommended to perform fine-tuning on [Google Colab](https://colab.research.google.com/drive/1omMhfYKrAAQ7a6zOCsyqpla-wU-QyfZn?usp=sharing) because the original VITS has some dependencies that are difficult to configure. -### How long does it take? +### How long does it take? 1. Install dependencies (2 min) -2. Record at least 10 your own voice (5 min) -3. Fine-tune (30 min) +2. Record at least 20 your own voice (5~10 min) +3. Upload your character voices, which should be a `.zip` file, +it's file structure should be like: +``` +Your-zip-file.zip +├───Character_name_1 +├ ├───xxx.wav +├ ├───... +├ ├───yyy.mp3 +├ └───zzz.wav +├───Character_name_2 +├ ├───xxx.wav +├ ├───... +├ ├───yyy.mp3 +├ └───zzz.wav +├───... +├ +└───Character_name_n + ├───xxx.wav + ├───... + ├───yyy.mp3 + └───zzz.wav +``` +Note that the format & name of the audio files does not matter as long as they are audio files. +You can either choose to perform step 2, 3, or both, depending on your needs. +4. Fine-tune (30 min) After everything is done, download the fine-tuned model & model config ## Inference or Usage (Currently support Windows only) 0. Remember to download your fine-tuned model! 1. Download the latest release -2. Put your model & config file into the folder `VC_inference`, make sure to rename the model to `G_latest.pth` and config file to `finetune_speaker.json` +2. Put your model & config file into the folder `inference`, make sure to rename the model to `G_latest.pth` and config file to `finetune_speaker.json` 3. The file structure should be as follows: ```shell -VC_inference -├───VC_inference.exe +inference +├───inference.exe ├───... ├───finetune_speaker.json └───G_latest.json ``` -4. run `VC_inference.exe`, the browser should pop up automatically. +4. run `inference.exe`, the browser should pop up automatically. diff --git a/README_EN.md b/README_EN.md index 259cb27..891dc3e 100644 --- a/README_EN.md +++ b/README_EN.md @@ -9,13 +9,13 @@ Welcome to play around with the base model, a Trilingual Anime VITS! ### Currently Supported Tasks: - [x] Convert user's voice to characters listed [here](https://github.com/SongtingLiu/VITS_voice_conversion/blob/main/configs/finetune_speaker.json) - [x] Chinese, English, Japanese TTS with user's voice -- [ ] Chinese, English, Japanese TTS with custom characters... +- [x] Chinese, English, Japanese TTS with custom characters! ### Currently Supported Characters for TTS & VC: -- [x] Umamusume Pretty Derby -- [x] Sanoba Witch -- [x] Genshin Impact -- [ ] Custom characters... +- [x] Umamusume Pretty Derby (Used as base model pretraining) +- [x] Sanoba Witch (Used as base model pretraining) +- [x] Genshin Impact (Used as base model pretraining) +- [x] Any character you wish as long as you have their voices! @@ -24,22 +24,46 @@ Welcome to play around with the base model, a Trilingual Anime VITS! It's recommended to perform fine-tuning on [Google Colab](https://colab.research.google.com/drive/1omMhfYKrAAQ7a6zOCsyqpla-wU-QyfZn?usp=sharing) because the original VITS has some dependencies that are difficult to configure. -### How long does it take? +### How long does it take? 1. Install dependencies (2 min) -2. Record at least 10 your own voice (5 min) -3. Fine-tune (30 min) +2. Record at least 20 your own voice (5~10 min) +3. Upload your character voices, which should be a `.zip` file, +it's file structure should be like: +``` +Your-zip-file.zip +├───Character_name_1 +├ ├───xxx.wav +├ ├───... +├ ├───yyy.mp3 +├ └───zzz.wav +├───Character_name_2 +├ ├───xxx.wav +├ ├───... +├ ├───yyy.mp3 +├ └───zzz.wav +├───... +├ +└───Character_name_n + ├───xxx.wav + ├───... + ├───yyy.mp3 + └───zzz.wav +``` +Note that the format & name of the audio files does not matter as long as they are audio files. +You can either choose to perform step 2, 3, or both, depending on your needs. +4. Fine-tune (30 min) After everything is done, download the fine-tuned model & model config ## Inference or Usage (Currently support Windows only) 0. Remember to download your fine-tuned model! 1. Download the latest release -2. Put your model & config file into the folder `VC_inference`, make sure to rename the model to `G_latest.pth` and config file to `finetune_speaker.json` +2. Put your model & config file into the folder `inference`, make sure to rename the model to `G_latest.pth` and config file to `finetune_speaker.json` 3. The file structure should be as follows: ```shell -VC_inference -├───VC_inference.exe +inference +├───inference.exe ├───... ├───finetune_speaker.json └───G_latest.json ``` -4. run `VC_inference.exe`, the browser should pop up automatically. +4. run `inference.exe`, the browser should pop up automatically. diff --git a/README_ZH.md b/README_ZH.md index 5d4d716..4b4c57b 100644 --- a/README_ZH.md +++ b/README_ZH.md @@ -24,7 +24,31 @@ English Documentation Please Click [here](https://github.com/SongtingLiu/VITS_vo 进行微调任务，因为VITS在多语言情况下的某些环境依赖相当难以配置。 ### 在Google Colab里，我需要花多长时间？ 1. 安装依赖 (2 min) -2. 录入你自己的声音，至少20条3~4秒的短句 (5 min) +2. 录入你自己的声音，至少20条3~4秒的短句 (5~10 min) +3. 上传你希望加入的其它角色声音，用一个`.zip`文件打包 +文件结构应该如下所示: +``` +Your-zip-file.zip +├───Character_name_1 +├ ├───xxx.wav +├ ├───... +├ ├───yyy.mp3 +├ └───zzz.wav +├───Character_name_2 +├ ├───xxx.wav +├ ├───... +├ ├───yyy.mp3 +├ └───zzz.wav +├───... +├ +└───Character_name_n + ├───xxx.wav + ├───... + ├───yyy.mp3 + └───zzz.wav +``` +注意音频的格式和名称都不重要，只要它们是音频文件。 +你可以选择进行步骤2或3，或二者一起，取决于你的需求。 3. 进行微调 (30 min) 微调结束后可以直接下载微调好的模型，日后在本地运行（不需要GPU） @@ -32,14 +56,14 @@ English Documentation Please Click [here](https://github.com/SongtingLiu/VITS_vo ## 本地运行和推理 0. 记得下载微调好的模型和config文件！ 1. 下载最新的Release包（在Github页面的右侧） -2. 把下载的模型和config文件放在 `VC_inference`文件夹下, 确保模型的文件名为 `G_latest.pth` ，config文件名为 `finetune_speaker.json` +2. 把下载的模型和config文件放在 `inference`文件夹下, 确保模型的文件名为 `G_latest.pth` ，config文件名为 `finetune_speaker.json` 3. 一切准备就绪后，文件结构应该如下所示: ```shell -VC_inference -├───VC_inference.exe +inference +├───inference.exe ├───... ├───finetune_speaker.json └───G_latest.json ``` -4. 运行 `VC_inference.exe`, 浏览器会自动弹出窗口. +4. 运行 `inference.exe`, 浏览器会自动弹出窗口.