Skip to content
Extraits de code Groupes Projets
Valider e2feca85 rédigé par Sting's avatar Sting
Parcourir les fichiers

Update README

parent 05b0f296
Branches
Aucune étiquette associée trouvée
1 requête de fusion!5Install process
...@@ -46,37 +46,42 @@ If we ever want to use an AI to identify syllables without a reference lyrics fi ...@@ -46,37 +46,42 @@ If we ever want to use an AI to identify syllables without a reference lyrics fi
## Requirements ## Requirements
- MKVToolnix (at least the CLI utils) - MKVToolnix (at least the CLI utils)
- FFmpeg
- Python >= 3.8 - Python >= 3.8
Optional :
- PyTorch for custom model training : follow the instructions [here](https://pytorch.org/get-started/locally/)
All other python modules can be installed directly through pip, see further. All other python modules can be installed directly through pip, see further.
This project requires at least Python 3.8, and using a virtual environment is strongly recommended. ## Install
To install the dependencies, execute in the project directory :
```bash
$ python -m venv env # create the virtual environment, do it once
$ source env/bin/activate # use the virtual environement
# Install the required python modules The simplest way to install Autokara is through PIP :
$ pip install -r requirements.txt ```bash
# Using HTTPS
$ pip install git+https://git.iiens.net/bakaclub/autokara.git
# To exit the virtual environment # Or SSH
$ deactivate $ pip install git+ssh://git@git.iiens.net:bakaclub/autokara.git
``` ```
Having a CUDA-capable GPU is optional, but can greatly reduce processing time in some situations. Or you can clone the repo and use `pip install <repo_directory>` if you prefer.
To use the custom phonetic mapping for Japanese Romaji, you need to update manually (for now) the g2p DB (within the venv): To use the custom phonetic mappings for Japanese Romaji and other non-English languages, you need to update manually (for now) the g2p DB (within the venv):
```bash ```bash
$ cp g2p/mappings/langs/rji/* env/lib/python3.11/site-packages/g2p/mappings/langs/rji/ $ autokara-gen-lang
```
#Then update :
$ g2p update If you plan on contributing to development, the use of a virtual environment is recommended :
```bash
$ python -m venv env # create the virtual environment, do it once
$ source env/bin/activate # use the virtual environement
$ pip install git+ssh://git@git.iiens.net:bakaclub/autokara.git # install autokara
# To exit the virtual environment
$ deactivate
``` ```
Having a CUDA-capable GPU is optional, but can greatly reduce processing time in some situations.
# Use # Use
...@@ -89,22 +94,22 @@ To use Autokara, you need : ...@@ -89,22 +94,22 @@ To use Autokara, you need :
To execute AutoKara on a MKV video file and an ASS file containing the lyrics (ASS will be overwritten): To execute AutoKara on a MKV video file and an ASS file containing the lyrics (ASS will be overwritten):
```bash ```bash
$ python autokara.py video.mkv lyrics.ass $ autokara video.mkv lyrics.ass
``` ```
To output to a different file (and keep the original) : To output to a different file (and keep the original) :
```bash ```bash
$ python autokara.py video.mkv lyrics.ass -o output.ass $ autokara video.mkv lyrics.ass -o output.ass
``` ```
To execute AutoKara on a (pre-extracted) WAV (or OGG, MP3, ...) vocals file, pass the `--vocals` flag : To execute AutoKara on a (pre-extracted) WAV (or OGG, MP3, ...) vocals file, pass the `--vocals` flag :
```bash ```bash
$ python autokara.py vocals.wav output.ass --vocals $ autokara vocals.wav output.ass --vocals
``` ```
To use a phonetic transcription optimized for a specific language, use `--lang` (or `-l`) : To use a phonetic transcription optimized for a specific language, use `--lang` (or `-l`) :
```bash ```bash
$ python autokara.py vocals.wav output.ass --lang jp $ autokara vocals.wav output.ass --lang jp
``` ```
Available languages are : Available languages are :
``` ```
...@@ -114,7 +119,7 @@ en : English ...@@ -114,7 +119,7 @@ en : English
Full help for all options is available with : Full help for all options is available with :
```bash ```bash
$ python autokara.py -h $ autokara -h
``` ```
## Useful scripts ## Useful scripts
...@@ -143,7 +148,7 @@ A visualization tool, mainly intended for debug. ...@@ -143,7 +148,7 @@ A visualization tool, mainly intended for debug.
Does the same as autokara.py, but instead of writing to a file, plots a graphic with onset times, spectrogram, probability curves,... Does the same as autokara.py, but instead of writing to a file, plots a graphic with onset times, spectrogram, probability curves,...
Does not work on video files, only separated vocals audio files Does not work on video files, only separated vocals audio files
```bash ```bash
$ python plot_syls.py vocals.wav lyrics.ass $ autokara-plot vocals.wav lyrics.ass
``` ```
......
0% Chargement en cours ou .
You are about to add 0 people to the discussion. Proceed with caution.
Veuillez vous inscrire ou vous pour commenter