From 3fc6566285e6fdd32c8b870c74efea06b679bab4 Mon Sep 17 00:00:00 2001 From: Tomodachi94 <68489118+Tomodachi94@users.noreply.github.com> Date: Sat, 23 Jan 2021 21:35:00 -0800 Subject: [PATCH 1/8] Add instructions for using with venv --- README.md | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 29217c5f7..d4220aee0 100644 --- a/README.md +++ b/README.md @@ -32,12 +32,15 @@ SV2TTS is a three-stage deep learning framework that allows to create a numerica ## Setup -### 1. Install Requirements +### 1. Prepare prerequisites -**Python 3.6 or 3.7** is needed to run the toolbox. +**Python 3.6+** is needed to run the toolbox. * Install [PyTorch](https://pytorch.org/get-started/locally/) (>=1.0.1). * Install [ffmpeg](https://ffmpeg.org/download.html#get-packages). +* (Highly recommended, as RTVC uses outdated dependancies) Setup a virtual environment with [`venv`](https://docs.python.org/3/library/venv.html) by running `python -m venv .venv`. + * Activate the virtual environment with `.venv/Scripts/activate`. + * Do note you will need to run this command before running anything in the toolbox if you used this to install dependancies, otherwise it will return an error saying it's missing some dependancies. * Run `pip install -r requirements.txt` to install the remaining necessary packages. ### 2. Download Pretrained Models From 9415546a41ddcf244fe909e85c96228867a78227 Mon Sep 17 00:00:00 2001 From: Tomodachi94 <68489118+Tomodachi94@users.noreply.github.com> Date: Sun, 24 Jan 2021 00:00:37 -0800 Subject: [PATCH 2/8] Remove insta --- README.md | 43 ++----------------------------------------- 1 file changed, 2 insertions(+), 41 deletions(-) diff --git a/README.md b/README.md index d4220aee0..21adffed7 100644 --- a/README.md +++ b/README.md @@ -30,44 +30,5 @@ SV2TTS is a three-stage deep learning framework that allows to create a numerica **25/06/19:** Experimental support for low-memory GPUs (~2gb) added for the synthesizer. Pass `--low_mem` to `demo_cli.py` or `demo_toolbox.py` to enable it. It adds a big overhead, so it's not recommended if you have enough VRAM. -## Setup - -### 1. Prepare prerequisites - -**Python 3.6+** is needed to run the toolbox. - -* Install [PyTorch](https://pytorch.org/get-started/locally/) (>=1.0.1). -* Install [ffmpeg](https://ffmpeg.org/download.html#get-packages). -* (Highly recommended, as RTVC uses outdated dependancies) Setup a virtual environment with [`venv`](https://docs.python.org/3/library/venv.html) by running `python -m venv .venv`. - * Activate the virtual environment with `.venv/Scripts/activate`. - * Do note you will need to run this command before running anything in the toolbox if you used this to install dependancies, otherwise it will return an error saying it's missing some dependancies. -* Run `pip install -r requirements.txt` to install the remaining necessary packages. - -### 2. Download Pretrained Models -Download the latest [here](https://github.com/CorentinJ/Real-Time-Voice-Cloning/wiki/Pretrained-models). - -### 3. (Optional) Test Configuration -Before you download any dataset, you can begin by testing your configuration with: - -`python demo_cli.py` - -If all tests pass, you're good to go. - -### 4. (Optional) Download Datasets -For playing with the toolbox alone, I only recommend downloading [`LibriSpeech/train-clean-100`](https://www.openslr.org/resources/12/train-clean-100.tar.gz). Extract the contents as `/LibriSpeech/train-clean-100` where `` is a directory of your choosing. Other datasets are supported in the toolbox, see [here](https://github.com/CorentinJ/Real-Time-Voice-Cloning/wiki/Training#datasets). You're free not to download any dataset, but then you will need your own data as audio files or you will have to record it with the toolbox. - -### 5. Launch the Toolbox -You can then try the toolbox: - -`python demo_toolbox.py -d ` -or -`python demo_toolbox.py` - -depending on whether you downloaded any datasets. If you are running an X-server or if you have the error `Aborted (core dumped)`, see [this issue](https://github.com/CorentinJ/Real-Time-Voice-Cloning/issues/11#issuecomment-504733590). - -### 6. (Optional) Enable GPU Support -Note: Enabling GPU support is a lot of work. You will want to set this up if you are going to train your own models. Somebody took the time to make [a better guide](https://poorlydocumented.com/2019/11/installing-corentinjs-real-time-voice-cloning-project-on-windows-10-from-scratch/) on how to install everything. I recommend using it. - -This command installs additional GPU dependencies and recommended packages: `pip install -r requirements_gpu.txt` - -Additionally, you will need to ensure GPU drivers are properly installed and that your CUDA version matches your PyTorch and Tensorflow installations. +## Installation and Setup +See [INSTALL.md](INSTALL.md) for installation instructions for complete instructions. From b7c075369830c150577678d90e132102fbad9fcb Mon Sep 17 00:00:00 2001 From: Tomodachi94 <68489118+Tomodachi94@users.noreply.github.com> Date: Sun, 24 Jan 2021 00:03:00 -0800 Subject: [PATCH 3/8] Fix typo --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 21adffed7..0c0dbd8f9 100644 --- a/README.md +++ b/README.md @@ -31,4 +31,4 @@ SV2TTS is a three-stage deep learning framework that allows to create a numerica ## Installation and Setup -See [INSTALL.md](INSTALL.md) for installation instructions for complete instructions. +See [INSTALL.md](INSTALL.md) for complete installation and setup instructions. From ee3fd6ce2ab98da8212d343e55b026e3e43846e3 Mon Sep 17 00:00:00 2001 From: Tomodachi94 <68489118+Tomodachi94@users.noreply.github.com> Date: Sun, 24 Jan 2021 00:09:02 -0800 Subject: [PATCH 4/8] Move old install instructions to INSTALL.md --- INSTALL.md | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 INSTALL.md diff --git a/INSTALL.md b/INSTALL.md new file mode 100644 index 000000000..5fe3fe982 --- /dev/null +++ b/INSTALL.md @@ -0,0 +1,41 @@ +## Setup + + ### 1. Prepare prerequisites + + **Python 3.6+** is needed to run the toolbox. + + * Install [PyTorch](https://pytorch.org/get-started/locally/) (>=1.0.1). + * Install [ffmpeg](https://ffmpeg.org/download.html#get-packages). + * (Highly recommended, as RTVC uses outdated dependancies) Setup a virtual environment with [`venv`](https://docs.python.org/3/library/venv.html) by running `python -m venv .venv`. + * Activate the virtual environment with `.venv/Scripts/activate`. + * Do note you will need to run this command before running anything in the toolbox if you used this to install dependancies, otherwise it will return an error saying it's missing some dependancies. + * Run `pip install -r requirements.txt` to install the remaining necessary packages. + + ### 2. Download Pretrained Models + Download the latest [here](https://github.com/CorentinJ/Real-Time-Voice-Cloning/wiki/Pretrained-models). + + ### 3. (Optional) Test Configuration + Before you download any dataset, you can begin by testing your configuration with: + + `python demo_cli.py` + + If all tests pass, you're good to go. + + ### 4. (Optional) Download Datasets + For playing with the toolbox alone, I only recommend downloading [`LibriSpeech/train-clean-100`](https://www.openslr.org/resources/12/train-clean-100.tar.gz). Extract the contents as `/LibriSpeech/train-clean-100` where `` is a directory of your choosing. Other datasets are supported in the toolbox, see [here](https://github.com/CorentinJ/Real-Time-Voice-Cloning/wiki/Training#datasets). You're free not to download any dataset, but then you will need your own data as audio files or you will have to record it with the toolbox. + + ### 5. Launch the Toolbox + You can then try the toolbox: + + `python demo_toolbox.py -d ` + or + `python demo_toolbox.py` + + depending on whether you downloaded any datasets. If you are running an X-server or if you have the error `Aborted (core dumped)`, see [this issue](https://github.com/CorentinJ/Real-Time-Voice-Cloning/issues/11#issuecomment-504733590). + + ### 6. (Optional) Enable GPU Support + Note: Enabling GPU support is a lot of work. You will want to set this up if you are going to train your own models. Somebody took the time to make [a better guide](https://poorlydocumented.com/2019/11/installing-corentinjs-real-time-voice-cloning-project-on-windows-10-from-scratch/) on how to install everything. I recommend using it. + + This command installs additional GPU dependencies and recommended packages: `pip install -r requirements_gpu.txt` + + Additionally, you will need to ensure GPU drivers are properly installed and that your CUDA version matches your PyTorch and Tensorflow installations. From b0c5d92db21ea961445e1f5ec70e843bbef74619 Mon Sep 17 00:00:00 2001 From: Tomodachi94 <68489118+Tomodachi94@users.noreply.github.com> Date: Sun, 24 Jan 2021 00:27:23 -0800 Subject: [PATCH 5/8] Add Linux Install Instructions Source: #615 Attribution for instructions go to @FreddyFeuerstein , proofread by @blue-fish and adapted for file by your truly --- INSTALL.md | 68 +++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 67 insertions(+), 1 deletion(-) diff --git a/INSTALL.md b/INSTALL.md index 5fe3fe982..6a50508ca 100644 --- a/INSTALL.md +++ b/INSTALL.md @@ -1,4 +1,6 @@ -## Setup +# Setup + +## Windows (Partially tested) ### 1. Prepare prerequisites @@ -39,3 +41,67 @@ This command installs additional GPU dependencies and recommended packages: `pip install -r requirements_gpu.txt` Additionally, you will need to ensure GPU drivers are properly installed and that your CUDA version matches your PyTorch and Tensorflow installations. + +## Ubuntu 20.04 install instructions (tested) +### 1. Add repositories +``` +sudo add-apt-repository universe +sudo add-apt-repository ppa:deadsnakes/ppa +``` + +### 2. Install software +``` +snap install ffmpeg +sudo apt install python3.6 python3.6-dev python3 python3-pip git +pip3 install virtualenv +``` + +Additional steps are needed to overcome bugs with portaudio and QT: + +* Portaudio bugfix: https://stackoverflow.com/a/60824906 + +``` +sudo apt install libasound2-dev +git clone -b alsapatch https://github.com/gglockner/portaudio +cd portaudio +./configure && make +sudo make install +sudo ldconfig +cd .. +``` + +* QT bugfix: https://askubuntu.com/a/1069502 + +``` +sudo apt install --reinstall libxcb-xinerama0 +``` + +### 3. Make a virtual environment and activate it +``` +~/.local/bin/virtualenv --python python36 rtvc +source rtvc/bin/activate +``` + +### 4. Download RTVC +``` +git clone --depth 1 https://github.com/CorentinJ/Real-Time-Voice-Cloning.git +``` + +### 5. Install requirements +``` +cd Real-Time-Voice-Cloning +pip install torch +pip install -r requirements.txt +pip install webrtcvad +``` + +### 6. Get pretrained models +``` +wget https://www.dropbox.com/s/5udq50bkpw2hipy/pretrained.zip?dl=1 -O pretrained.zip +unzip pretrained.zip +``` + +### 7. Launch toolbox +``` +python demo_toolbox.py +``` From 5824e17f6fbe7d12db378241f896f4b765ad1d52 Mon Sep 17 00:00:00 2001 From: Tomodachi94 <68489118+Tomodachi94@users.noreply.github.com> Date: Sun, 24 Jan 2021 01:27:27 -0800 Subject: [PATCH 6/8] Add Mac OSX install instructions Based off of the Linux instructions by @FreddyFeuerstein with recommendations by @blue-fish --- INSTALL.md | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/INSTALL.md b/INSTALL.md index 6a50508ca..ede051381 100644 --- a/INSTALL.md +++ b/INSTALL.md @@ -105,3 +105,39 @@ unzip pretrained.zip ``` python demo_toolbox.py ``` + +## Mac OSX (Untested) +### Install prerequisites +- [Python 3.7](https://www.python.org/downloads/mac-osx/) +- homebrew with `/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"` +- ffmpeg with `brew install ffmpeg` + +### 3. Make a virtual environment and activate it +``` +~/.local/bin/virtualenv --python python36 rtvc +source rtvc/bin/activate +``` + +### 4. Download RTVC +``` +git clone --depth 1 https://github.com/CorentinJ/Real-Time-Voice-Cloning.git +``` + +### 5. Install requirements +``` +cd Real-Time-Voice-Cloning +pip install torch +pip install -r requirements.txt +pip install webrtcvad +``` + +### 6. Get pretrained models +``` +wget https://www.dropbox.com/s/5udq50bkpw2hipy/pretrained.zip?dl=1 -O pretrained.zip +unzip pretrained.zip +``` + +### 7. Launch toolbox +``` +python demo_toolbox.py +``` From 3760e6de6f85b76a51c765e11a3d3cacfca253b5 Mon Sep 17 00:00:00 2001 From: Tomodachi94 <68489118+Tomodachi94@users.noreply.github.com> Date: Sun, 24 Jan 2021 01:41:53 -0800 Subject: [PATCH 7/8] Link to Python website for download --- INSTALL.md | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/INSTALL.md b/INSTALL.md index ede051381..6158b0d02 100644 --- a/INSTALL.md +++ b/INSTALL.md @@ -1,11 +1,9 @@ -# Setup +# Installation and Setup Guide for Real Time Voice Cloning ## Windows (Partially tested) ### 1. Prepare prerequisites - - **Python 3.6+** is needed to run the toolbox. - + * Install [Python](https://www.python.org). * Install [PyTorch](https://pytorch.org/get-started/locally/) (>=1.0.1). * Install [ffmpeg](https://ffmpeg.org/download.html#get-packages). * (Highly recommended, as RTVC uses outdated dependancies) Setup a virtual environment with [`venv`](https://docs.python.org/3/library/venv.html) by running `python -m venv .venv`. From 135550cd48d8d19b6b23930ccac61dab41d3ab6e Mon Sep 17 00:00:00 2001 From: Tomodachi94 <68489118+Tomodachi94@users.noreply.github.com> Date: Wed, 27 Jan 2021 13:21:43 -0800 Subject: [PATCH 8/8] Specify version of Python in Windows instructions --- INSTALL.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/INSTALL.md b/INSTALL.md index 6158b0d02..d79afc029 100644 --- a/INSTALL.md +++ b/INSTALL.md @@ -3,7 +3,7 @@ ## Windows (Partially tested) ### 1. Prepare prerequisites - * Install [Python](https://www.python.org). + * Install [Python](https://www.python.org) 3.7. Any other version will not work. * Install [PyTorch](https://pytorch.org/get-started/locally/) (>=1.0.1). * Install [ffmpeg](https://ffmpeg.org/download.html#get-packages). * (Highly recommended, as RTVC uses outdated dependancies) Setup a virtual environment with [`venv`](https://docs.python.org/3/library/venv.html) by running `python -m venv .venv`.