From 285615d67c4d877724faec74748594966a5001e6 Mon Sep 17 00:00:00 2001 From: wok Date: Thu, 1 Aug 2024 11:01:20 +0900 Subject: [PATCH] update --- README.md | 70 +++++++++++++++++----------------------------------- README_en.md | 62 +++++++++++++++------------------------------- README_ko.md | 61 +++++++++++++++------------------------------ 3 files changed, 62 insertions(+), 131 deletions(-) diff --git a/README.md b/README.md index 7ecc6959..bfa59369 100644 --- a/README.md +++ b/README.md @@ -6,6 +6,14 @@ - Beatrice V2 トレーニングコード公開!!! - [トレーニングコードリポジトリ](https://huggingface.co/fierce-cats/beatrice-trainer) - [コラボ版](https://github.com/w-okada/beatrice-trainer-colab) +- v.2.0.50-alpha + - [こちらを参照](https://github.com/w-okada/voice-changer/tree/v.2) + - improve: + - クライアントモードの性能改善 + - Macエディションにネイティブクライアント同梱 + - bugfix: + - BeatriceV2変換時の入力デバイス変更時(サンプリングレートが異なると落ちる)の例外対応 + - サーバモードからクライアントモードへ変更時に音が壊れる対策 - v.2.0.47-alpha - [こちらを参照](https://github.com/w-okada/voice-changer/tree/v.2) - feature: @@ -14,31 +22,25 @@ - beatrice のデフォルト話者IDの変更 - モデルファイル名が長いときのエラー対策 - モニターデバイスをnoneにしたときの対応。 -- v2.0.45-alpha - - [こちらを参照](https://github.com/w-okada/voice-changer/tree/v.2) - - bugfix - - 音量調整 - - - # VC Client とは 1. 各種音声変換 AI(VC, Voice Conversion)を用いてリアルタイム音声変換を行うためのクライアントソフトウェアです。サポートしている音声変換 AI は次のものになります。 - サポートする音声変換 AI （サポート VC） - - [MMVC](https://github.com/isletennos/MMVC_Trainer) - - [so-vits-svc](https://github.com/svc-develop-team/so-vits-svc) + - [MMVC](https://github.com/isletennos/MMVC_Trainer) (only v1) + - [so-vits-svc](https://github.com/svc-develop-team/so-vits-svc) (only v1) - [RVC(Retrieval-based-Voice-Conversion)](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI) - - [DDSP-SVC](https://github.com/yxlllc/DDSP-SVC) - - [Beatrice JVS Corpus Edition](https://prj-beatrice.com/) * experimental, (***NOT MIT License*** see [readme](https://github.com/w-okada/voice-changer/blob/master/server/voice_changer/Beatrice/)) * Only for Windows, CPU dependent + - [DDSP-SVC](https://github.com/yxlllc/DDSP-SVC) (only v1) + - [Beatrice JVS Corpus Edition](https://prj-beatrice.com/) * experimental, (***NOT MIT License*** see [readme](https://github.com/w-okada/voice-changer/blob/master/server/voice_changer/Beatrice/)) * Only for Windows, CPU dependent (only for v1) + - [Beatrice v2](https://prj-beatrice.com/) (only for v2) 1. 本ソフトウェアは、ネットワークを介した利用も可能であり、ゲームなどの高負荷なアプリケーションと同時に使用する場合などに音声変換処理の負荷を外部にオフロードすることができます。 ![image](https://user-images.githubusercontent.com/48346627/206640768-53f6052d-0a96-403b-a06c-6714a0b7471d.png) 3. 複数のプラットフォームに対応しています。 -- Windows, Mac(M1), Linux, Google Colab (MMVC のみ) +- Windows, Mac(M1), Linux, Google Colab # 使用方法 @@ -51,16 +53,19 @@ ## (1) 事前ビルド済みの Binary での利用 -- 実行形式のバイナリをダウンロードして実行することができます。 - - チュートリアルは[こちら](tutorials/tutorial_rvc_ja_latest.md)をご覧ください。([ネットワークのトラブルシュート](https://github.com/w-okada/voice-changer/blob/master/tutorials/trouble_shoot_communication_ja.md)) - [Google Colaboratory](https://github.com/w-okada/voice-changer/tree/v.2/w_okada's_Voice_Changer_version_2_x.ipynb) で簡単にお試しいただけるようになりました。左上の Open in Colab のボタンから起動できます。 -- Windows 版と Mac 版を提供しています。 - +- Windows 版と Mac 版を提供しています。[Hugging Face](https://huggingface.co/wok000/vcclient000/tree/main)からダウンロードできます。 +- v2 for windows + - `vcclient_win_std_xxx.zip`をダウンロードして使用してください。gpuを使用しない(ある程度高性能なCPUでの)音声変換や、directmlを用いてgpu(amd, nvidia)を活用した音声変換が可能です。v2では、torch, onnxいずれも対応可能です。 + - nvidiaのgpuをお持ちの方は`vcclient_win_cuda_xxx.zip`を使用することでより高速な音声変換ができます。 +- v2 for Mac(apple silicon) + - `vcclient_mac_xxx.zip`をダウンロードして使用してください。 +- v1 - Windows かつ Nvidia の GPU をご使用の方は、ONNX(cpu,cuda), PyTorch(cpu,cuda)をダウンロードしてください。 - Windows かつ AMD/Intel の GPU をご使用の方は、ONNX(cpu,DirectML), PyTorch(cpu,cuda)をダウンロードしてください。AMD/Intel の GPU は onnx のモデルを使用する場合のみ有効になります。 - いずれの GPU のサポート状況についても、PyTorch、Onnxruntime がサポートしている場合のみ有効になります。 @@ -77,28 +82,8 @@ - DDPS-SVC の encoder は hubert-soft のみ対応です。 - ダウンロードはこちらから。 +[hugging face](https://huggingface.co/wok000/vcclient000/tree/main) -| Version | OS | フレームワーク | link | サポート VC | サイズ | -| ----------- | --- | ------------------------------------- | ------------------------------------------------------------------- | ----------------------------------------------------------------------------------- | ------ | -| v.1.5.3.18a | mac | ONNX(cpu), PyTorch(cpu,mps) | N/A | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC | 797MB | -| | win | ONNX(cpu,cuda), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3240MB | -| | win | ONNX(cpu,DirectML), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3125MB | -| v.1.5.3.17b | mac | ONNX(cpu), PyTorch(cpu,mps) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC | 797MB | -| | win | ONNX(cpu,cuda), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3240MB | -| | win | ONNX(cpu,DirectML), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3125MB | -| v.1.5.3.16a | mac | ONNX(cpu), PyTorch(cpu,mps) | N/A | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC | 797MB | -| | win | ONNX(cpu,cuda), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3240MB | -| | win | ONNX(cpu,DirectML), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3125MB | -| v.1.5.3.15 | mac | ONNX(cpu), PyTorch(cpu,mps) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC | 797MB | -| | win | ONNX(cpu,cuda), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC | 3240MB | -| | win | ONNX(cpu,DirectML), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC | 3125MB | - -(\*1) Google Drive からダウンロードできない方は[hugging_face](https://huggingface.co/wok000/vcclient000/tree/main)からダウンロードしてみてください -(\*2) 開発者が AMD のグラフィックボードを持っていないので動作確認していません。onnxruntime-directml を同梱しただけのものです。 -(\*3) 解凍や起動が遅い場合、ウィルス対策ソフトのチェックが走っている可能性があります。ファイルやフォルダを対象外にして実行してみてください。（自己責任です） - - -https://huggingface.co/wok000/vcclient000/resolve/main/MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.18.zip?download=true ## (2) Docker や Anaconda など環境構築を行った上での利用 @@ -116,17 +101,6 @@ Anaconda の仮想環境上での実行は、[サーバ開発者向けのペー - [通信編](tutorials/trouble_shoot_communication_ja.md) -# リアルタイム性（MMVC） - -GPU を使用するとほとんどタイムラグなく変換可能です。 - -https://twitter.com/DannadoriYellow/status/1613483372579545088?s=20&t=7CLD79h1F3dfKiTb7M8RUQ - -CPU でも最近のであればそれなりの速度で変換可能。 - -https://twitter.com/DannadoriYellow/status/1613553862773997569?s=20&t=7CLD79h1F3dfKiTb7M8RUQ - -古い CPU( i7-4770)だと、1000msec くらいかかってしまう。 # 開発者の署名について diff --git a/README_en.md b/README_en.md index 87e88e75..97f0700c 100644 --- a/README_en.md +++ b/README_en.md @@ -6,6 +6,13 @@ - Beatrice V2 Training Code Released!!! - [Training Code Repository](https://huggingface.co/fierce-cats/beatrice-trainer) - [Colab Version](https://github.com/w-okada/beatrice-trainer-colab) +- v.2.0.50-alpha + - improve: + - Improved performance in client mode + - Bundled native client with Mac edition + - bugfix: + - Fixed exception when changing input device during BeatriceV2 conversion (if the sampling rate is different, it crashes) + - Fixed issue where sound gets corrupted when switching from server mode to client mode - v.2.0.47-alpha - [HERE](https://github.com/w-okada/voice-changer/tree/v.2) - feature: @@ -14,21 +21,17 @@ - Changed the default speaker ID for Beatrice - Fixed errors when model file names are too long - Handled situation when monitor device is set to none. -- v2.0.45-alpha - - [HERE](https://github.com/w-okada/voice-changer/tree/v.2) - - bugfix - - volume control - # What is VC Client 1. This is a client software for performing real-time voice conversion using various Voice Conversion (VC) AI. The supported AI for voice conversion are as follows. -- [MMVC](https://github.com/isletennos/MMVC_Trainer) -- [so-vits-svc](https://github.com/svc-develop-team/so-vits-svc) +- [MMVC](https://github.com/isletennos/MMVC_Trainer) (only v1) +- [so-vits-svc](https://github.com/svc-develop-team/so-vits-svc) (only v1) - [RVC(Retrieval-based-Voice-Conversion)](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI) -- [DDSP-SVC](https://github.com/yxlllc/DDSP-SVC) -- [Beatrice JVS Corpus Edition](https://prj-beatrice.com/) * experimental, (***NOT MIT License*** see [readme](https://github.com/w-okada/voice-changer/blob/master/server/voice_changer/Beatrice/)) * Only for Windows, CPU dependent +- [DDSP-SVC](https://github.com/yxlllc/DDSP-SVC) (only v1) +- [Beatrice JVS Corpus Edition](https://prj-beatrice.com/) * experimental, (***NOT MIT License*** see [readme](https://github.com/w-okada/voice-changer/blob/master/server/voice_changer/Beatrice/)) * Only for Windows, CPU dependent (only v1) + - [Beatrice v2](https://prj-beatrice.com/) (only for v2) 1. Distribute the load by running Voice Changer on a different PC The real-time voice changer of this application works on a server-client configuration. By running the MMVC server on a separate PC, you can run it while minimizing the impact on other resource-intensive processes such as gaming commentary. @@ -57,8 +60,13 @@ It can be used in two main ways, in order of difficulty: -- We offer Windows and Mac versions. - +- We offer Windows and Mac versions on [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) +- v2 for Windows + - Please download and use `vcclient_win_std_xxx.zip`. You can perform voice conversion using a reasonably high-performance CPU without a GPU, or by utilizing DirectML to leverage GPUs (AMD, Nvidia). v2 supports both torch and onnx. + - If you have an Nvidia GPU, you can achieve faster voice conversion by using `vcclient_win_cuda_xxx.zip`. +- v2 for Mac (Apple Silicon) + - Please download and use `vcclient_mac_xxx.zip`. +- v1 - If you are using a Windows and Nvidia GPU, please download ONNX (cpu, cuda), PyTorch (cpu, cuda). - If you are using a Windows and AMD/Intel GPU, please download ONNX (cpu, DirectML) and PyTorch (cpu, cuda). AMD/Intel GPUs are only enabled for ONNX models. - In either case, for GPU support, PyTorch and Onnxruntime are only enabled if supported. @@ -72,26 +80,7 @@ It can be used in two main ways, in order of difficulty: - The encoder of DDPS-SVC only supports hubert-soft. -- Download (When you cannot download from google drive, try [hugging_face](https://huggingface.co/wok000/vcclient000/tree/main)) - -| Version | OS | Framework | link | support VC | size | -| ----------- | --- | ------------------------------------- | ------------------------------------------------------------------- | ----------------------------------------------------------------------------------- | ------ | -| v.1.5.3.18a | mac | ONNX(cpu), PyTorch(cpu,mps) | N/A | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC | 797MB | -| | win | ONNX(cpu,cuda), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3240MB | -| | win | ONNX(cpu,DirectML), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3125MB | -| v.1.5.3.17b | mac | ONNX(cpu), PyTorch(cpu,mps) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC | 797MB | -| | win | ONNX(cpu,cuda), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3240MB | -| | win | ONNX(cpu,DirectML), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3125MB | -| v.1.5.3.16a | mac | ONNX(cpu), PyTorch(cpu,mps) | N/A | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC | 797MB | -| | win | ONNX(cpu,cuda), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3240MB | -| | win | ONNX(cpu,DirectML), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3125MB | -| v.1.5.3.15 | mac | ONNX(cpu), PyTorch(cpu,mps) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC | 797MB | -| | win | ONNX(cpu,cuda), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC | 3240MB | -| | win | ONNX(cpu,DirectML), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC | 3125MB | - -(\*1) You can also download from [hugging_face](https://huggingface.co/wok000/vcclient000/tree/main) -(\*2) The developer does not have an AMD graphics card, so it has not been tested. This package only includes onnxruntime-directml. -(\*3) If unpacking or starting is slow, there is a possibility that virus checking is running on your antivirus software. Please try running it with the file or folder excluded from the target. (At your own risk) +- [Download from hugging face](https://huggingface.co/wok000/vcclient000/tree/main) ## (2) Usage after setting up the environment such as Docker or Anaconda @@ -107,17 +96,6 @@ To run on Anaconda venv, see [server developer's guide](README_dev_en.md) To run on Linux using an AMD GPU, see [setup guide linux](tutorials/tutorial_anaconda_amd_rocm.md) -# Real-time performance - -Conversion is almost instantaneous when using GPU. - -https://twitter.com/DannadoriYellow/status/1613483372579545088?s=20&t=7CLD79h1F3dfKiTb7M8RUQ - -Even with CPU, recent ones can perform conversions at a reasonable speed. - -https://twitter.com/DannadoriYellow/status/1613553862773997569?s=20&t=7CLD79h1F3dfKiTb7M8RUQ - -With an old CPU (i7-4770), it takes about 1000 msec for conversion. # Software Signing diff --git a/README_ko.md b/README_ko.md index 2a2e1cec..2d94710d 100644 --- a/README_ko.md +++ b/README_ko.md @@ -6,6 +6,14 @@ - Beatrice V2 훈련 코드 공개!!! - [훈련 코드 리포지토리](https://huggingface.co/fierce-cats/beatrice-trainer) - [Colab 버전](https://github.com/w-okada/beatrice-trainer-colab) +- v.2.0.50-alpha + - [여기를 참조하십시오](https://github.com/w-okada/voice-changer/tree/v.2) + - 개선사항: + - 클라이언트 모드의 성능 개선 + - Mac 에디션에 네이티브 클라이언트 포함 + - 버그수정: + - BeatriceV2 변환 중 입력 장치를 변경할 때(샘플링 레이트가 다르면 크래시 발생) 예외 처리 + - 서버 모드에서 클라이언트 모드로 전환 시 음질 손상 문제 해결 - v.2.0.47-alpha - [여기를 참조하십시오](https://github.com/w-okada/voice-changer/tree/v.2) - 기능: @@ -14,21 +22,18 @@ - Beatrice의 기본 화자 ID 변경 - 모델 파일 이름이 너무 길 때의 오류 수정 - 모니터 장치를 none으로 설정했을 때의 처리. -- v2.0.45-alpha - - [여기를 참조하십시오](https://github.com/w-okada/voice-changer/tree/v.2) - - bugfix - - 음량 조절 # VC Client란 1. 각종 음성 변환 AI(VC, Voice Conversion)를 활용해 실시간 음성 변환을 하기 위한 클라이언트 소프트웨어입니다. 지원하는 음성 변환 AI는 다음과 같습니다. - 지원하는 음성 변환 AI (지원 VC) - - [MMVC](https://github.com/isletennos/MMVC_Trainer) - - [so-vits-svc](https://github.com/svc-develop-team/so-vits-svc) + - [MMVC](https://github.com/isletennos/MMVC_Trainer) (only v1) + - [so-vits-svc](https://github.com/svc-develop-team/so-vits-svc) (only v1) - [RVC(Retrieval-based-Voice-Conversion)](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI) - - [DDSP-SVC](https://github.com/yxlllc/DDSP-SVC) - - [Beatrice JVS Corpus Edition](https://prj-beatrice.com/) * experimental, (***NOT MIT License*** see [readme](https://github.com/w-okada/voice-changer/blob/master/server/voice_changer/Beatrice/)) * Only for Windows, CPU dependent + - [DDSP-SVC](https://github.com/yxlllc/DDSP-SVC) (only v1) + - [Beatrice JVS Corpus Edition](https://prj-beatrice.com/) * experimental, (***NOT MIT License*** see [readme](https://github.com/w-okada/voice-changer/blob/master/server/voice_changer/Beatrice/)) * Only for Windows, CPU dependent (only v1) + - [Beatrice v2](https://prj-beatrice.com/) (only for v2) - 1. 이 소프트웨어는 네트워크를 통한 사용도 가능하며, 게임 등 부하가 큰 애플리케이션과 동시에 사용할 경우 음성 변화 처리의 부하를 외부로 돌릴 수도 있습니다. @@ -57,8 +62,13 @@ -- Windows 버전과 Mac 버전을 제공하고 있습니다. - +- Windows 버전과 Mac 버전을 제공하고 있습니다. [Hugging Face](https://huggingface.co/wok000/vcclient000/tree/main)에서 다운로드할 수 있습니다. +- Windows용 v2 + - `vcclient_win_std_xxx.zip`를 다운로드하여 사용하세요. GPU를 사용하지 않고도 (어느 정도 고성능의) CPU를 사용한 음성 변환이나, DirectML을 사용해 GPU(AMD, Nvidia)를 활용한 음성 변환이 가능합니다. v2에서는 torch와 onnx 모두를 지원합니다. + - Nvidia GPU를 가지고 계신 분들은 `vcclient_win_cuda_xxx.zip`를 사용하시면 더 빠른 음성 변환이 가능합니다. +- Mac (Apple Silicon)용 v2 + - `vcclient_mac_xxx.zip`를 다운로드하여 사용하세요. +- v1 - Windows와 NVIDIA GPU를 사용하는 분은 ONNX(cpu, cuda), PyTorch(cpu, cuda)를 다운로드하세요. - Windows와 AMD/Intel GPU를 사용하는 분은 ONNX(cpu, DirectML), PyTorch(cpu, cuda)를 다운로드하세요 AMD/Intel GPU는 ONNX 모델을 사용할 때만 적용됩니다. - 그 외 GPU도 PyTorch, Onnxruntime가 지원할 경우에만 적용됩니다. @@ -74,26 +84,6 @@ - DDPS-SVC의 encoder는 hubert-soft만 지원합니다. -- 다운로드는 아래에서 하세요. - -| Version | OS | 프레임워크 | 링크 | 지원 VC | 파일 크기 | -| ----------- | --- | ------------------------------------- | ------------------------------------------------------------------- | ----------------------------------------------------------------------------------- | --------- | -| v.1.5.3.18a | mac | ONNX(cpu), PyTorch(cpu,mps) | N/A | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC | 797MB | -| | win | ONNX(cpu,cuda), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3240MB | -| | win | ONNX(cpu,DirectML), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3125MB | -| v.1.5.3.17b | mac | ONNX(cpu), PyTorch(cpu,mps) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC | 797MB | -| | win | ONNX(cpu,cuda), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3240MB | -| | win | ONNX(cpu,DirectML), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3125MB | -| v.1.5.3.16a | mac | ONNX(cpu), PyTorch(cpu,mps) | N/A | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC | 797MB | -| | win | ONNX(cpu,cuda), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3240MB | -| | win | ONNX(cpu,DirectML), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC, Beatrice | 3125MB | -| v.1.5.3.15 | mac | ONNX(cpu), PyTorch(cpu,mps) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC | 797MB | -| | win | ONNX(cpu,cuda), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC | 3240MB | -| | win | ONNX(cpu,DirectML), PyTorch(cpu,cuda) | [hugging face](https://huggingface.co/wok000/vcclient000/tree/main) | MMVC v.1.5.x, MMVC v.1.3.x, so-vits-svc 4.0, RVC, DDSP-SVC, Diffusion-SVC | 3125MB | - -(\*1) Google Drive에서 다운로드가 안 되는 분은 [hugging_face](https://huggingface.co/wok000/vcclient000/tree/main)에서 시도해 보세요 -(\*2) 개발자가 AMD 그래픽카드를 갖고 있지 않아서 작동 확인을 할 수 없습니다. onnxruntime-directml를 같이 첨부한 것이 전부입니다. -(\*3) 압축 해제나 실행 속도가 느릴 경우에는 바이러스 검사가 진행 중일 가능성이 있습니다. 파일과 폴더를 검사 대상 제외를 한 후에 시도해 보세요. (이에 개발자는 책임이 없음) ## (2) Docker나 Anaconda 등으로 구축된 개발 환경에서 사용 @@ -111,17 +101,6 @@ Anaconda 가상 환경에서 실행은 [서버 개발자용 문서](README_dev_k - [통신편](tutorials/trouble_shoot_communication_ko.md) -# 실시간성(MMVC) - -GPU를 사용하면 시간 차가 거의 없이 변환할 수 있습니다. - -https://twitter.com/DannadoriYellow/status/1613483372579545088?s=20&t=7CLD79h1F3dfKiTb7M8RUQ - -CPU도 최근 제품이라면 어느 정도 빠르게 변환할 수 있습니다. - -https://twitter.com/DannadoriYellow/status/1613553862773997569?s=20&t=7CLD79h1F3dfKiTb7M8RUQ - -오래된 CPU(i7-4770)면, 1000msec 정도 걸립니다. # 개발자 서명에 대하여