mirror of
https://github.com/rakuri255/UltraSinger.git
synced 2026-11-20 13:07:52 +09:00
Merge branch 'main' of https://github.com/rakuri255/UltraSinger
This commit is contained in:
commit
b758d08d14
6 files changed
+1032
-31
No files matched your search
@@ -17,7 +17,7 @@
|
||||
|
||||
> ⚠️ _This project is still under development!_
|
||||
|
||||
UltraSinger is a tool to automatically create UltraStar.txt, midi and notes from music.
|
||||
UltraSinger is a tool to automatically create UltraStar.txt, midi and notes from music.
|
||||
It automatically pitches UltraStar files, adding text and tapping to UltraStar files and creates separate UltraStar karaoke files.
|
||||
It also can re-pitch current UltraStar files and calculates the possible in-game score.
|
||||
|
||||
@@ -77,7 +77,7 @@ This will help me a lot to keep this project alive and improve it.
|
||||
|
||||
### Run
|
||||
|
||||
* In root folder just run `run_on_windows.bat` or `run_on_linux.sh` to start the app.
|
||||
* In root folder just run `run_on_windows.bat`, `run_on_linux.sh` or `run_on_macos.command` to start the app.
|
||||
* Now you can use the UltraSinger source code with `py UltraSinger.py [opt] [mode] [transcription] [pitcher] [extra]`. See [How to use](#how-to-use) for more information.
|
||||
|
||||
## 📖 How to use the App
|
||||
@@ -85,23 +85,23 @@ This will help me a lot to keep this project alive and improve it.
|
||||
_Not all options working now!_
|
||||
```commandline
|
||||
UltraSinger.py [opt] [mode] [transcription] [pitcher] [extra]
|
||||
|
||||
|
||||
[opt]
|
||||
-h This help text.
|
||||
-i Ultrastar.txt
|
||||
audio like .mp3, .wav, youtube link
|
||||
-o Output folder
|
||||
|
||||
|
||||
[mode]
|
||||
## if INPUT is audio ##
|
||||
default (Full Automatic Mode) - Creates all, depending on command line options
|
||||
--interactive - Interactive Mode. All options are asked at runtime for easier configuration
|
||||
|
||||
|
||||
# Single file creation selection is in progress, you currently getting all!
|
||||
(-u Create ultrastar txt file) # In Progress
|
||||
(-m Create midi file) # In Progress
|
||||
(-s Create sheet file) # In Progress
|
||||
|
||||
|
||||
## if INPUT is ultrastar.txt ##
|
||||
default Creates all
|
||||
|
||||
@@ -117,13 +117,13 @@ _Not all options working now!_
|
||||
--language Override the language detected by whisper, does not affect transcription but steps after transcription
|
||||
--whisper_batch_size Reduce if low on GPU mem >> ((default) is 16)
|
||||
--whisper_compute_type Change to "int8" if low on GPU mem (may reduce accuracy) >> ((default) is "float16" for cuda devices, "int8" for cpu)
|
||||
--keep_numbers Numbers will be transcribed as numerics instead of as words
|
||||
|
||||
--keep_numbers Numbers will be transcribed as numerics instead of as words
|
||||
|
||||
[pitcher]
|
||||
# Default is crepe
|
||||
--crepe tiny|full >> ((default) is full)
|
||||
--crepe_step_size unit is miliseconds >> ((default) is 10)
|
||||
|
||||
|
||||
[extra]
|
||||
--disable_hyphenation Disable word hyphenation. Hyphenation is enabled by default.
|
||||
--disable_separation Disable track separation. Track separation is enabled by default.
|
||||
@@ -135,7 +135,7 @@ _Not all options working now!_
|
||||
--musescore_path path to MuseScore executable
|
||||
--keep_numbers Transcribe numbers as digits and not words
|
||||
--ffmpeg Path to ffmpeg and ffprobe executable
|
||||
|
||||
|
||||
[yt-dlp]
|
||||
--cookiefile File name where cookies should be read from
|
||||
|
||||
@@ -196,8 +196,8 @@ For the first test run, use the `tiny`, to be accurate use the `large-v2` model.
|
||||
|
||||
##### Whisper languages
|
||||
|
||||
Currently provided default language models are `en, fr, de, es, it, ja, zh, nl, uk, pt`.
|
||||
If the language is not in this list, you need to find a phoneme-based ASR model from
|
||||
Currently provided default language models are `en, fr, de, es, it, ja, zh, nl, uk, pt`.
|
||||
If the language is not in this list, you need to find a phoneme-based ASR model from
|
||||
[🤗 huggingface model hub](https://huggingface.co). It will download automatically.
|
||||
|
||||
Example for romanian:
|
||||
@@ -207,9 +207,9 @@ Example for romanian:
|
||||
|
||||
#### ✍️ Hyphenation
|
||||
|
||||
Is on by default. Can also be deactivated if hyphenation does not produce
|
||||
anything useful. Note that the word is simply split,
|
||||
without paying attention to whether the separated word really
|
||||
Is on by default. Can also be deactivated if hyphenation does not produce
|
||||
anything useful. Note that the word is simply split,
|
||||
without paying attention to whether the separated word really
|
||||
starts at the place or is heard. To disable:
|
||||
|
||||
```commandline
|
||||
@@ -229,11 +229,11 @@ If you want solid accurate, then use the `full` model.
|
||||
|
||||
### 👄 Separation
|
||||
|
||||
The vocals are separated from the audio before they are passed to the models. If problems occur with this,
|
||||
The vocals are separated from the audio before they are passed to the models. If problems occur with this,
|
||||
you have the option to disable this function; in which case the original audio file is used instead.
|
||||
|
||||
```commandline
|
||||
-i XYZ --disable_separation
|
||||
-i XYZ --disable_separation
|
||||
```
|
||||
|
||||
### Sheet Music
|
||||
@@ -262,11 +262,11 @@ You can choose between different format versions. The default is `1.2.0`.
|
||||
|
||||
### 🏆 Ultrastar Score Calculation
|
||||
|
||||
The score that the singer in the audio would receive will be measured.
|
||||
You get 2 scores, simple and accurate. You wonder where the difference is?
|
||||
Ultrastar is not interested in pitch hights. As long as it is in the pitch range A-G you get one point.
|
||||
This makes sense for the game, because otherwise men don't get points for high female voices and women don't get points
|
||||
for low male voices. Accurate is the real tone specified in the txt. I had txt files where the pitch was in a range not
|
||||
The score that the singer in the audio would receive will be measured.
|
||||
You get 2 scores, simple and accurate. You wonder where the difference is?
|
||||
Ultrastar is not interested in pitch hights. As long as it is in the pitch range A-G you get one point.
|
||||
This makes sense for the game, because otherwise men don't get points for high female voices and women don't get points
|
||||
for low male voices. Accurate is the real tone specified in the txt. I had txt files where the pitch was in a range not
|
||||
singable by humans, but you could still reach the 10k points in the game. The accuracy is important here, because from
|
||||
this MIDI and sheet are created. And you also want to have accurate files
|
||||
|
||||
|
||||
Executable
+7
@@ -0,0 +1,7 @@
|
||||
#!/bin/bash
|
||||
cd ..
|
||||
cd ..
|
||||
python3.10 -m venv .venv
|
||||
source .venv/bin/activate
|
||||
pip install -r requirements-macos.txt
|
||||
pip install torch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1
|
||||
+2
-2
@@ -3,9 +3,9 @@ requires = ["setuptools", "setuptools-scm"]
|
||||
build-backend = "setuptools.build_meta"
|
||||
|
||||
[project]
|
||||
requires-python = "3.10"
|
||||
name = "UltraSinger"
|
||||
dynamic = ["dependencies", "optional-dependencies"]
|
||||
requires-python = "==3.10"
|
||||
|
||||
[tool.setuptools.dynamic]
|
||||
dependencies = { file = ["requirements.in"] }
|
||||
@@ -19,4 +19,4 @@ profile = "black"
|
||||
[tool.pytest.ini_options]
|
||||
pythonpath = [
|
||||
"src",
|
||||
]
|
||||
]
|
||||
@@ -0,0 +1,959 @@
|
||||
#
|
||||
# This file is autogenerated by pip-compile with Python 3.10
|
||||
# by the following command:
|
||||
#
|
||||
# pip-compile --output-file=requirements-macos.txt requirements-linux.txt requirements.in
|
||||
#
|
||||
# NOTE: The linux file was manually edited to change tensorflow-io-gcs-filesystem to 0.37.1
|
||||
#
|
||||
absl-py==2.3.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# keras
|
||||
# tensorboard
|
||||
# tensorflow
|
||||
aiohappyeyeballs==2.6.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# aiohttp
|
||||
aiohttp==3.12.9
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# fsspec
|
||||
aiosignal==1.3.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# aiohttp
|
||||
alembic==1.16.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# optuna
|
||||
antlr4-python3-runtime==4.9.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# omegaconf
|
||||
appdirs==1.4.4
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyhyphen
|
||||
asteroid-filterbanks==0.4.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-audio
|
||||
astroid==3.3.10
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pylint
|
||||
astunparse==1.6.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# tensorflow
|
||||
async-timeout==5.0.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# aiohttp
|
||||
attrs==25.3.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# aiohttp
|
||||
audioread==3.0.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# librosa
|
||||
av==14.4.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# faster-whisper
|
||||
black==25.1.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
certifi==2025.4.26
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# requests
|
||||
cffi==1.17.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# soundfile
|
||||
chardet==5.2.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# music21
|
||||
charset-normalizer==3.4.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# requests
|
||||
click==8.2.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# black
|
||||
# nltk
|
||||
# typer
|
||||
cloudpickle==3.1.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# submitit
|
||||
colorama==0.4.6
|
||||
# via -r requirements-linux.txt
|
||||
coloredlogs==15.0.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# onnxruntime
|
||||
colorlog==6.9.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# optuna
|
||||
contourpy==1.3.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# matplotlib
|
||||
crepe==0.0.16
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
ctranslate2==4.4.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# faster-whisper
|
||||
# whisperx
|
||||
cycler==0.12.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# matplotlib
|
||||
dataclasses==0.6
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
dataclasses-json==0.6.7
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
decorator==5.2.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# librosa
|
||||
demucs==4.0.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
dill==0.4.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pylint
|
||||
docopt==0.6.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# num2words
|
||||
# pyannote-metrics
|
||||
# pyannote-pipeline
|
||||
dora-search==0.1.12
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# demucs
|
||||
einops==0.8.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# demucs
|
||||
# pyannote-audio
|
||||
exceptiongroup==1.3.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pytest
|
||||
faster-whisper==1.1.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# whisperx
|
||||
ffmpeg-python==0.2.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
filelock==3.18.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# huggingface-hub
|
||||
# pyannote-pipeline
|
||||
# torch
|
||||
# transformers
|
||||
flatbuffers==25.2.10
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# onnxruntime
|
||||
# tensorflow
|
||||
fonttools==4.58.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# matplotlib
|
||||
frozenlist==1.6.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# aiohttp
|
||||
# aiosignal
|
||||
fsspec[http]==2025.5.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# huggingface-hub
|
||||
# lightning
|
||||
# pytorch-lightning
|
||||
# torch
|
||||
future==1.0.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# ffmpeg-python
|
||||
gast==0.6.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# tensorflow
|
||||
google-pasta==0.2.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# tensorflow
|
||||
greenlet==3.2.3
|
||||
# via -r requirements-linux.txt
|
||||
grpcio==1.72.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# tensorboard
|
||||
# tensorflow
|
||||
h5py==3.13.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# crepe
|
||||
# keras
|
||||
# tensorflow
|
||||
hf-xet==1.2.0
|
||||
# via huggingface-hub
|
||||
hmmlearn==0.3.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# crepe
|
||||
huggingface-hub==0.32.4
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# faster-whisper
|
||||
# pyannote-audio
|
||||
# speechbrain
|
||||
# tokenizers
|
||||
# transformers
|
||||
humanfriendly==10.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# coloredlogs
|
||||
hyperpyyaml==1.2.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# speechbrain
|
||||
idna==3.10
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# requests
|
||||
# yarl
|
||||
imageio==2.37.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# crepe
|
||||
iniconfig==2.1.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pytest
|
||||
inputimeout==1.0.4
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
isort==6.0.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
# pylint
|
||||
jinja2==3.1.6
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# torch
|
||||
joblib==1.5.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# librosa
|
||||
# music21
|
||||
# nltk
|
||||
# scikit-learn
|
||||
# speechbrain
|
||||
jsonpickle==4.1.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# music21
|
||||
julius==0.2.7
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# demucs
|
||||
# torch-audiomentations
|
||||
keras==3.10.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# tensorflow
|
||||
kiwisolver==1.4.8
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# matplotlib
|
||||
lameenc==1.8.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# demucs
|
||||
langcodes==3.5.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
language-data==1.3.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# langcodes
|
||||
levenshtein==0.27.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# python-levenshtein
|
||||
libclang==18.1.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# tensorflow
|
||||
librosa==0.9.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
lightning==2.5.1.post0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-audio
|
||||
lightning-utilities==0.14.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# lightning
|
||||
# pytorch-lightning
|
||||
# torchmetrics
|
||||
llvmlite==0.44.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# numba
|
||||
mako==1.3.10
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# alembic
|
||||
marisa-trie==1.2.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# language-data
|
||||
markdown==3.8
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# tensorboard
|
||||
markdown-it-py==3.0.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# rich
|
||||
markupsafe==3.0.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# jinja2
|
||||
# mako
|
||||
# werkzeug
|
||||
marshmallow==3.26.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# dataclasses-json
|
||||
matplotlib==3.10.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
# crepe
|
||||
# music21
|
||||
# pyannote-metrics
|
||||
mccabe==0.7.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pylint
|
||||
mdurl==0.1.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# markdown-it-py
|
||||
mido==1.3.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pretty-midi
|
||||
ml-dtypes==0.5.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# keras
|
||||
# tensorflow
|
||||
more-itertools==10.7.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# music21
|
||||
mpmath==1.3.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# sympy
|
||||
multidict==6.4.4
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# aiohttp
|
||||
# yarl
|
||||
music21==9.7.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
musicbrainzngs==0.7.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
mypy-extensions==1.1.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# black
|
||||
# typing-inspect
|
||||
namex==0.1.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# keras
|
||||
networkx==3.4.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# torch
|
||||
nltk==3.9.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# whisperx
|
||||
num2words==0.5.14
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
numba==0.61.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# librosa
|
||||
# resampy
|
||||
numpy==1.26.4
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
# asteroid-filterbanks
|
||||
# contourpy
|
||||
# crepe
|
||||
# ctranslate2
|
||||
# h5py
|
||||
# hmmlearn
|
||||
# imageio
|
||||
# keras
|
||||
# librosa
|
||||
# matplotlib
|
||||
# ml-dtypes
|
||||
# music21
|
||||
# numba
|
||||
# onnxruntime
|
||||
# openunmix
|
||||
# optuna
|
||||
# pandas
|
||||
# pretty-midi
|
||||
# pyannote-core
|
||||
# pyannote-metrics
|
||||
# pytorch-metric-learning
|
||||
# resampy
|
||||
# scikit-learn
|
||||
# scipy
|
||||
# soundfile
|
||||
# speechbrain
|
||||
# tensorboard
|
||||
# tensorboardx
|
||||
# tensorflow
|
||||
# torchmetrics
|
||||
# transformers
|
||||
omegaconf==2.3.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# dora-search
|
||||
# pyannote-audio
|
||||
onnxruntime==1.22.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# faster-whisper
|
||||
openunmix==1.3.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# demucs
|
||||
opt-einsum==3.4.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# tensorflow
|
||||
optree==0.16.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# keras
|
||||
optuna==4.3.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-pipeline
|
||||
packaging==24.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
# black
|
||||
# huggingface-hub
|
||||
# keras
|
||||
# librosa
|
||||
# lightning
|
||||
# lightning-utilities
|
||||
# marshmallow
|
||||
# matplotlib
|
||||
# mido
|
||||
# onnxruntime
|
||||
# optuna
|
||||
# pooch
|
||||
# pytest
|
||||
# pytorch-lightning
|
||||
# speechbrain
|
||||
# tensorboard
|
||||
# tensorboardx
|
||||
# tensorflow
|
||||
# torch-pitch-shift
|
||||
# torchmetrics
|
||||
# transformers
|
||||
pandas==2.3.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-database
|
||||
# pyannote-metrics
|
||||
# whisperx
|
||||
pathspec==0.12.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# black
|
||||
pillow==11.2.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# imageio
|
||||
# matplotlib
|
||||
platformdirs==4.3.8
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# black
|
||||
# pooch
|
||||
# pylint
|
||||
pluggy==1.6.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pytest
|
||||
pooch==1.8.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# librosa
|
||||
pretty-midi==0.2.10
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
primepy==1.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# torch-pitch-shift
|
||||
propcache==0.3.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# aiohttp
|
||||
# yarl
|
||||
protobuf==5.29.5
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# onnxruntime
|
||||
# tensorboard
|
||||
# tensorboardx
|
||||
# tensorflow
|
||||
pyannote-audio==3.3.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# whisperx
|
||||
pyannote-core==5.0.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-audio
|
||||
# pyannote-database
|
||||
# pyannote-metrics
|
||||
# pyannote-pipeline
|
||||
pyannote-database==5.1.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-audio
|
||||
# pyannote-metrics
|
||||
# pyannote-pipeline
|
||||
pyannote-metrics==3.2.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-audio
|
||||
pyannote-pipeline==3.0.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-audio
|
||||
pycparser==2.22
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# cffi
|
||||
pydub==0.25.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
pygments==2.19.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pytest
|
||||
# rich
|
||||
pyhyphen==4.0.4
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
pylint==3.3.7
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
pyparsing==3.2.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# matplotlib
|
||||
pyreadline3==3.5.4
|
||||
# via -r requirements-linux.txt
|
||||
pytest==8.4.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
python-dateutil==2.9.0.post0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# matplotlib
|
||||
# pandas
|
||||
python-levenshtein==0.27.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
pytorch-lightning==2.5.1.post0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# lightning
|
||||
pytorch-metric-learning==2.8.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-audio
|
||||
pytz==2025.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pandas
|
||||
pyyaml==6.0.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# ctranslate2
|
||||
# demucs
|
||||
# huggingface-hub
|
||||
# hyperpyyaml
|
||||
# lightning
|
||||
# omegaconf
|
||||
# optuna
|
||||
# pyannote-database
|
||||
# pyannote-pipeline
|
||||
# pytorch-lightning
|
||||
# transformers
|
||||
rapidfuzz==3.13.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# levenshtein
|
||||
regex==2024.11.6
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# nltk
|
||||
# transformers
|
||||
requests==2.32.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# huggingface-hub
|
||||
# music21
|
||||
# pooch
|
||||
# pyhyphen
|
||||
# tensorflow
|
||||
# transformers
|
||||
resampy==0.4.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# crepe
|
||||
# librosa
|
||||
retrying==1.3.4
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# dora-search
|
||||
rich==14.0.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# keras
|
||||
# pyannote-audio
|
||||
# typer
|
||||
ruamel-yaml==0.18.12
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# hyperpyyaml
|
||||
ruamel-yaml-clib==0.2.12
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# ruamel-yaml
|
||||
safetensors==0.5.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# transformers
|
||||
scikit-learn==1.6.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# crepe
|
||||
# hmmlearn
|
||||
# librosa
|
||||
# pyannote-metrics
|
||||
# pyannote-pipeline
|
||||
# pytorch-metric-learning
|
||||
scipy==1.15.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
# crepe
|
||||
# hmmlearn
|
||||
# librosa
|
||||
# pyannote-core
|
||||
# pyannote-metrics
|
||||
# scikit-learn
|
||||
# speechbrain
|
||||
semver==3.0.4
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-audio
|
||||
sentencepiece==0.2.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# speechbrain
|
||||
shellingham==1.5.4
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# typer
|
||||
six==1.17.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# astunparse
|
||||
# google-pasta
|
||||
# pretty-midi
|
||||
# python-dateutil
|
||||
# retrying
|
||||
# tensorboard
|
||||
# tensorflow
|
||||
sortedcontainers==2.4.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-core
|
||||
soundfile==0.13.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# librosa
|
||||
# pyannote-audio
|
||||
speechbrain==1.0.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-audio
|
||||
sqlalchemy==2.0.41
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# alembic
|
||||
# optuna
|
||||
submitit==1.5.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# dora-search
|
||||
sympy==1.14.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# onnxruntime
|
||||
# pyannote-metrics
|
||||
# torch
|
||||
tabulate==0.9.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-metrics
|
||||
tensorboard==2.19.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# tensorflow
|
||||
tensorboard-data-server==0.7.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# tensorboard
|
||||
tensorboardx==2.6.2.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-audio
|
||||
tensorflow==2.19.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
tensorflow-io-gcs-filesystem==0.37.1
|
||||
# via
|
||||
# -r requirements-linux.txt -- manually changed to 0.37.1 from 0.31.0
|
||||
# tensorflow
|
||||
termcolor==3.1.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# tensorflow
|
||||
threadpoolctl==3.6.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# scikit-learn
|
||||
tokenizers==0.21.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# faster-whisper
|
||||
# transformers
|
||||
tomli==2.2.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# alembic
|
||||
# black
|
||||
# pylint
|
||||
# pytest
|
||||
tomlkit==0.13.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pylint
|
||||
torch==2.7.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# asteroid-filterbanks
|
||||
# demucs
|
||||
# dora-search
|
||||
# julius
|
||||
# lightning
|
||||
# openunmix
|
||||
# pyannote-audio
|
||||
# pytorch-lightning
|
||||
# pytorch-metric-learning
|
||||
# speechbrain
|
||||
# torch-audiomentations
|
||||
# torch-pitch-shift
|
||||
# torchaudio
|
||||
# torchmetrics
|
||||
# whisperx
|
||||
torch-audiomentations==0.12.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-audio
|
||||
torch-pitch-shift==1.2.5
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# torch-audiomentations
|
||||
torchaudio==2.7.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# demucs
|
||||
# openunmix
|
||||
# pyannote-audio
|
||||
# speechbrain
|
||||
# torch-audiomentations
|
||||
# torch-pitch-shift
|
||||
# whisperx
|
||||
torchmetrics==1.7.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# lightning
|
||||
# pyannote-audio
|
||||
# pytorch-lightning
|
||||
tqdm==4.67.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
# demucs
|
||||
# faster-whisper
|
||||
# huggingface-hub
|
||||
# lightning
|
||||
# nltk
|
||||
# openunmix
|
||||
# optuna
|
||||
# pyannote-pipeline
|
||||
# pytorch-lightning
|
||||
# pytorch-metric-learning
|
||||
# speechbrain
|
||||
# transformers
|
||||
transformers==4.52.4
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# whisperx
|
||||
treetable==0.2.5
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# dora-search
|
||||
typer==0.16.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pyannote-database
|
||||
typing-extensions==4.14.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# alembic
|
||||
# asteroid-filterbanks
|
||||
# astroid
|
||||
# black
|
||||
# exceptiongroup
|
||||
# huggingface-hub
|
||||
# lightning
|
||||
# lightning-utilities
|
||||
# multidict
|
||||
# optree
|
||||
# pyannote-core
|
||||
# pytorch-lightning
|
||||
# rich
|
||||
# sqlalchemy
|
||||
# submitit
|
||||
# tensorflow
|
||||
# torch
|
||||
# typer
|
||||
# typing-inspect
|
||||
typing-inspect==0.9.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# dataclasses-json
|
||||
tzdata==2025.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# pandas
|
||||
unidecode==1.4.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
urllib3==2.4.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# requests
|
||||
webcolors==24.11.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# music21
|
||||
werkzeug==3.1.3
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# tensorboard
|
||||
wheel==0.45.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# astunparse
|
||||
# pyhyphen
|
||||
whisperx==3.3.1
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
wrapt==1.17.2
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# tensorflow
|
||||
yarl==1.20.0
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# aiohttp
|
||||
yt-dlp==2025.5.22
|
||||
# via
|
||||
# -r requirements-linux.txt
|
||||
# -r requirements.in
|
||||
|
||||
# The following packages are considered to be unsafe in a requirements file:
|
||||
# setuptools
|
||||
Executable
+2
@@ -0,0 +1,2 @@
|
||||
#!/bin/bash
|
||||
cd "$(dirname "$0")"; source .venv/bin/activate; cd src; exec bash
|
||||
@@ -1,5 +1,7 @@
|
||||
import musicbrainzngs
|
||||
import string
|
||||
import time
|
||||
from urllib.error import URLError
|
||||
from Levenshtein import ratio
|
||||
from dataclasses import dataclass
|
||||
from typing import Optional
|
||||
@@ -25,10 +27,22 @@ title_filter = [
|
||||
]
|
||||
|
||||
|
||||
MAX_RETRIES = 3
|
||||
|
||||
|
||||
def __clean_string(s: str) -> str:
|
||||
return s.translate(str.maketrans('', '', string.punctuation)).lower().strip()
|
||||
|
||||
|
||||
def __musicbrainz_request(func):
|
||||
for i in range(MAX_RETRIES):
|
||||
try:
|
||||
return func()
|
||||
except musicbrainzngs.musicbrainz.NetworkError:
|
||||
time.sleep(1)
|
||||
return None
|
||||
|
||||
|
||||
def search_musicbrainz(title: str, artist) -> SongInfo:
|
||||
# Musicbrainz API documentation
|
||||
# https://python-musicbrainzngs.readthedocs.io/en/latest/api/
|
||||
@@ -68,8 +82,12 @@ def __single_line_search(search_string):
|
||||
search_string = __clean_string(search_string)
|
||||
search_string = __filter_words(search_string)
|
||||
|
||||
artists = musicbrainzngs.search_artists(search_string, limit=10, artist=search_string)
|
||||
recordings = musicbrainzngs.search_recordings(search_string, limit=100, artistname=search_string)
|
||||
artists = __musicbrainz_request(lambda: musicbrainzngs.search_artists(search_string, limit=10, artist=search_string))
|
||||
recordings = __musicbrainz_request(lambda: musicbrainzngs.search_recordings(search_string, limit=100, artistname=search_string))
|
||||
|
||||
if artists is None or recordings is None:
|
||||
return None
|
||||
|
||||
found_artist = None
|
||||
|
||||
for record in recordings['recording-list']:
|
||||
@@ -114,8 +132,13 @@ def __multi_line_search(artist: str, title: str):
|
||||
artist1, title1 = artist, title
|
||||
artist2, title2 = title, artist
|
||||
|
||||
result1 = musicbrainzngs.search_recordings(recording=title1, limit=10, artist=artist1, artistname=artist1)
|
||||
result2 = musicbrainzngs.search_recordings(recording=title2, limit=10, artist=artist2, artistname=artist2)
|
||||
result1 = __musicbrainz_request(lambda: musicbrainzngs.search_recordings(recording=title1, limit=10, artist=artist1, artistname=artist1))
|
||||
result2 = __musicbrainz_request(lambda: musicbrainzngs.search_recordings(recording=title2, limit=10, artist=artist2, artistname=artist2))
|
||||
|
||||
if result1 is None:
|
||||
result1 = {'recording-count': 0, 'recording-list': []}
|
||||
if result2 is None:
|
||||
result2 = {'recording-count': 0, 'recording-list': []}
|
||||
|
||||
# Filter result to ['artist-credit-phrase'] == artist
|
||||
record1 = [x for x in result1['recording-list'] if
|
||||
@@ -157,8 +180,14 @@ def __get_image(recording) -> (bytes, str):
|
||||
if 'release-list' in recording:
|
||||
for release in recording['release-list']:
|
||||
try:
|
||||
image_data = musicbrainzngs.get_image_front(release['id'])
|
||||
image_list = musicbrainzngs.get_image_list(release['id'])
|
||||
image_data = __musicbrainz_request(lambda: musicbrainzngs.get_image_front(release['id']))
|
||||
if image_data is None:
|
||||
continue
|
||||
|
||||
image_list = __musicbrainz_request(lambda: musicbrainzngs.get_image_list(release['id']))
|
||||
if image_list is None:
|
||||
continue
|
||||
|
||||
for image in image_list['images']:
|
||||
if image['front']:
|
||||
image_url = image['image']
|
||||
@@ -179,7 +208,11 @@ def __get_year(recording):
|
||||
return year
|
||||
|
||||
release_group_id = recording['release-list'][0]['release-group']['id']
|
||||
release_group = musicbrainzngs.get_release_group_by_id(release_group_id)
|
||||
release_group = __musicbrainz_request(lambda: musicbrainzngs.get_release_group_by_id(release_group_id))
|
||||
|
||||
if release_group is None:
|
||||
return year
|
||||
|
||||
if 'first-release-date' not in release_group['release-group']:
|
||||
return year
|
||||
|
||||
|
||||
Reference in new issue
Block a user