mirror of
https://github.com/rakuri255/UltraSinger.git
synced 2026-11-20 13:07:52 +09:00
Merge branch 'drop_vosk_support' into CI
This commit is contained in:
commit
4d8a458f4c
32 files changed
+648
-240
No files matched your search
@@ -115,9 +115,7 @@ _Not all options working now!_
|
||||
--whisper Multilingual model > tiny|base|small|medium|large-v1|large-v2 >> ((default) is large-v2
|
||||
English-only model > tiny.en|base.en|small.en|medium.en
|
||||
--align_model Use other languages model for Whisper provided from huggingface.co
|
||||
|
||||
--vosk Needs model
|
||||
|
||||
|
||||
[pitcher]
|
||||
# Default is crepe
|
||||
--crepe tiny|small|medium|large|full >> ((default) is full)
|
||||
@@ -158,10 +156,7 @@ This re-pitch the audio and creates a new txt file.
|
||||
|
||||
### Transcriber
|
||||
|
||||
For transcription, `whisper` is used by default. It is more accurate than the other even with the `large` model.
|
||||
And it finds the language automatically.
|
||||
But anyway, it depends! Try the other one if `Whisper` does not suit you.
|
||||
Also keep in mind that while a larger model is more accurate, it also takes longer to transcribe.
|
||||
Keep in mind that while a larger model is more accurate, it also takes longer to transcribe.
|
||||
|
||||
#### Whisper
|
||||
|
||||
@@ -182,16 +177,6 @@ Example for romanian:
|
||||
-i XYZ --align_model "gigant/romanian-wav2vec2"
|
||||
```
|
||||
|
||||
#### Vosk
|
||||
|
||||
If you want to use `Vosk` than you need the model. It is not included. You can download it here [Link](https://alphacephei.com/vosk/models).
|
||||
Make sure you take the right language.
|
||||
For the first test run, use the `small model`, to be accurate use the `gigaspeech` model
|
||||
|
||||
```commandline
|
||||
-i XYZ -v "models\vosk-model-en-us-0.42-gigaspeech"
|
||||
```
|
||||
|
||||
#### Hyphenation
|
||||
|
||||
Is on by default. Can also be deactivated if hyphenation does not produce
|
||||
|
||||
@@ -0,0 +1,4 @@
|
||||
[tool.pytest.ini_options]
|
||||
pythonpath = [
|
||||
"src",
|
||||
]
|
||||
@@ -0,0 +1,56 @@
|
||||
"""Tests for whisper.py"""
|
||||
|
||||
import unittest
|
||||
from src.modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
from src.modules.Speech_Recognition.Whisper import convert_to_transcribed_data
|
||||
|
||||
|
||||
class ConvertToTranscribedDataTest(unittest.TestCase):
|
||||
def test_convert_to_transcribed_data(self):
|
||||
# Arrange
|
||||
result_aligned = {
|
||||
"segments": [
|
||||
{
|
||||
"words": [
|
||||
{"word": "UltraSinger", "start": 1.23, "end": 2.34, "confidence": 0.95},
|
||||
{"word": "is", "start": 2.34, "end": 3.45, "confidence": 0.9},
|
||||
{"word": "cool!", "start": 3.45, "end": 4.56, "confidence": 0.85},
|
||||
]
|
||||
},
|
||||
{
|
||||
"words": [
|
||||
{"word": "And", "start": 4.56, "end": 5.67, "confidence": 0.95},
|
||||
{"word": "will", "start": 5.67, "end": 6.78, "confidence": 0.9},
|
||||
{"word": "be", "start": 6.78, "end": 7.89, "confidence": 0.85},
|
||||
{"word": "better!", "start": 7.89, "end": 9.01, "confidence": 0.8},
|
||||
]
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
# Words should have space at the end
|
||||
expected_output = [
|
||||
TranscribedData(
|
||||
{"word": "UltraSinger ", "start": 1.23, "end": 2.34, "is_hyphen": None, "confidence": 0.95}),
|
||||
TranscribedData({"word": "is ", "start": 2.34, "end": 3.45, "is_hyphen": None, "confidence": 0.9}),
|
||||
TranscribedData({"word": "cool! ", "start": 3.45, "end": 4.56, "is_hyphen": None, "confidence": 0.85}),
|
||||
TranscribedData({"word": "And ", "start": 4.56, "end": 5.67, "is_hyphen": None, "confidence": 0.95}),
|
||||
TranscribedData({"word": "will ", "start": 5.67, "end": 6.78, "is_hyphen": None, "confidence": 0.9}),
|
||||
TranscribedData({"word": "be ", "start": 6.78, "end": 7.89, "is_hyphen": None, "confidence": 0.85}),
|
||||
TranscribedData({"word": "better! ", "start": 7.89, "end": 9.01, "is_hyphen": None, "confidence": 0.8}),
|
||||
]
|
||||
|
||||
# Act
|
||||
transcribed_data = convert_to_transcribed_data(result_aligned)
|
||||
|
||||
# Assert
|
||||
self.assertEqual(len(transcribed_data), len(expected_output))
|
||||
for i in range(len(transcribed_data)):
|
||||
self.assertEqual(transcribed_data[i].word, expected_output[i].word)
|
||||
self.assertEqual(transcribed_data[i].end, expected_output[i].end)
|
||||
self.assertEqual(transcribed_data[i].start, expected_output[i].start)
|
||||
self.assertEqual(transcribed_data[i].is_hyphen, expected_output[i].is_hyphen)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,17 @@
|
||||
"""Tests for hyphenation.py"""
|
||||
|
||||
import unittest
|
||||
from src.modules.Speech_Recognition.hyphenation import hyphenation
|
||||
from hyphen import Hyphenator
|
||||
|
||||
|
||||
def test_hypenation():
|
||||
"""Test case for hyphenation function."""
|
||||
|
||||
assert hyphenation("begegnen", Hyphenator("de_DE")) == ["be", "geg", "nen"]
|
||||
assert hyphenation(".b,e~g'eg*nen, ", Hyphenator("de_DE")) == [".b,e", "~g'eg", "*nen, "]
|
||||
assert hyphenation("Abend, ", Hyphenator("de_AT")) == None
|
||||
assert hyphenation("Abend.", Hyphenator("de_AT")) == None
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,138 @@
|
||||
"""Tests for the ultrastar_writer.py module."""
|
||||
|
||||
import unittest
|
||||
from unittest.mock import patch, mock_open
|
||||
from src.modules.Ultrastar.ultrastar_writer import create_ultrastar_txt_from_automation
|
||||
from src.modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
from src.modules.Ultrastar.ultrastar_txt import UltrastarTxtValue, UltrastarTxtTag
|
||||
|
||||
|
||||
class TestCreateUltrastarTxt(unittest.TestCase):
|
||||
def test_create_ultrastar_txt_from_automation_default_values(self):
|
||||
# Arrange
|
||||
bpm, note_numbers, transcribed_data, ultrastar_file_output = self.arrange()
|
||||
|
||||
# Assert default values
|
||||
class_under_test = UltrastarTxtValue()
|
||||
expected_calls = self.default_values(class_under_test)
|
||||
|
||||
self.act_and_assert(bpm, class_under_test, expected_calls, note_numbers, transcribed_data,
|
||||
ultrastar_file_output)
|
||||
|
||||
def test_create_ultrastar_txt_from_automation_full_values(self):
|
||||
# Arrange
|
||||
bpm, note_numbers, transcribed_data, ultrastar_file_output = self.arrange()
|
||||
|
||||
# Assert full values
|
||||
class_under_test = UltrastarTxtValue()
|
||||
class_under_test.artist = "artist"
|
||||
class_under_test.title = "title"
|
||||
class_under_test.year = "2023"
|
||||
class_under_test.language = "de"
|
||||
class_under_test.genre = "pop, rock"
|
||||
class_under_test.cover = "cover [CO].jpg"
|
||||
class_under_test.video = "video.mp4"
|
||||
class_under_test.mp3 = "music.mp3"
|
||||
|
||||
expected_calls = self.full_values(class_under_test)
|
||||
|
||||
self.act_and_assert(bpm, class_under_test, expected_calls, note_numbers, transcribed_data,
|
||||
ultrastar_file_output)
|
||||
|
||||
def arrange(self):
|
||||
# Arrange
|
||||
transcribed_data = [
|
||||
TranscribedData({
|
||||
"conf": 0.95,
|
||||
"word": "UltraSinger ",
|
||||
"end": 2.5,
|
||||
"start": 0.5
|
||||
}),
|
||||
TranscribedData({
|
||||
"conf": 0.9,
|
||||
"word": "is ",
|
||||
"end": 4.5,
|
||||
"start": 3.0
|
||||
}),
|
||||
TranscribedData({
|
||||
"conf": 0.85,
|
||||
"word": "cool! ",
|
||||
"end": 7.5,
|
||||
"start": 5.5
|
||||
}),
|
||||
]
|
||||
note_numbers = [1, 2, 3]
|
||||
ultrastar_file_output = "output.txt"
|
||||
bpm = 120
|
||||
return bpm, note_numbers, transcribed_data, ultrastar_file_output
|
||||
|
||||
def act_and_assert(self, bpm, default_ultrastar_class, expected_calls_default_values, note_numbers,
|
||||
transcribed_data, ultrastar_file_output):
|
||||
# Act
|
||||
mock_file = self.act(bpm, default_ultrastar_class, note_numbers, transcribed_data, ultrastar_file_output)
|
||||
|
||||
# Assert the file was opened and is utf-8
|
||||
mock_file.assert_called_once_with(ultrastar_file_output, "w", encoding='utf-8')
|
||||
|
||||
# Assert that expected_calls_default_values were written to the file
|
||||
mock_file_handle = mock_file.return_value.__enter__.return_value.write
|
||||
write_calls = [args[0][0] for args in mock_file_handle.call_args_list]
|
||||
self.assertEqual(write_calls, expected_calls_default_values)
|
||||
|
||||
@staticmethod
|
||||
def default_values(default_ultrastar_class):
|
||||
expected_calls = [
|
||||
f"#{UltrastarTxtTag.ARTIST}:{default_ultrastar_class.artist}\n",
|
||||
f"#{UltrastarTxtTag.TITLE}:{default_ultrastar_class.title}\n",
|
||||
f"#{UltrastarTxtTag.MP3}:{default_ultrastar_class.mp3}\n",
|
||||
f"#{UltrastarTxtTag.VIDEO}:{default_ultrastar_class.video}\n", # todo: video is optional
|
||||
f"#{UltrastarTxtTag.BPM}:390.0\n",
|
||||
f"#{UltrastarTxtTag.GAP}:500\n",
|
||||
f"#{UltrastarTxtTag.CREATOR}:{default_ultrastar_class.creator}\n",
|
||||
f"#{UltrastarTxtTag.FIXER}:{default_ultrastar_class.fixer}\n", # todo: fixer is special
|
||||
f"#{UltrastarTxtTag.COMMENT}:{default_ultrastar_class.comment}\n",
|
||||
": 0 52 1 UltraSinger \n",
|
||||
"- 52\n",
|
||||
": 65 39 2 is \n",
|
||||
"- 104\n",
|
||||
": 130 52 3 cool! \n",
|
||||
"E"
|
||||
]
|
||||
return expected_calls
|
||||
|
||||
@staticmethod
|
||||
def full_values(default_ultrastar_class):
|
||||
expected_calls = [
|
||||
f"#{UltrastarTxtTag.ARTIST}:{default_ultrastar_class.artist}\n",
|
||||
f"#{UltrastarTxtTag.TITLE}:{default_ultrastar_class.title}\n",
|
||||
f"#{UltrastarTxtTag.YEAR}:{default_ultrastar_class.year}\n",
|
||||
f"#{UltrastarTxtTag.LANGUAGE}:German\n",
|
||||
f"#{UltrastarTxtTag.GENRE}:{default_ultrastar_class.genre}\n",
|
||||
f"#{UltrastarTxtTag.COVER}:{default_ultrastar_class.cover}\n",
|
||||
f"#{UltrastarTxtTag.MP3}:{default_ultrastar_class.mp3}\n",
|
||||
f"#{UltrastarTxtTag.VIDEO}:{default_ultrastar_class.video}\n",
|
||||
f"#{UltrastarTxtTag.BPM}:390.0\n",
|
||||
f"#{UltrastarTxtTag.GAP}:500\n",
|
||||
f"#{UltrastarTxtTag.CREATOR}:{default_ultrastar_class.creator}\n",
|
||||
f"#{UltrastarTxtTag.FIXER}:{default_ultrastar_class.fixer}\n",
|
||||
f"#{UltrastarTxtTag.COMMENT}:{default_ultrastar_class.comment}\n",
|
||||
": 0 52 1 UltraSinger \n",
|
||||
"- 52\n",
|
||||
": 65 39 2 is \n",
|
||||
"- 104\n",
|
||||
": 130 52 3 cool! \n",
|
||||
"E"
|
||||
]
|
||||
return expected_calls
|
||||
|
||||
@staticmethod
|
||||
def act(bpm, default_ultrastar_class, note_numbers, transcribed_data, ultrastar_file_output):
|
||||
with patch("builtins.open", mock_open()) as mock_file:
|
||||
create_ultrastar_txt_from_automation(
|
||||
transcribed_data, note_numbers, ultrastar_file_output,
|
||||
default_ultrastar_class, bpm
|
||||
)
|
||||
return mock_file
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,93 @@
|
||||
"""Test the musicbrainz_client module."""
|
||||
|
||||
import unittest
|
||||
from unittest.mock import patch
|
||||
from src.modules.musicbrainz_client import get_music_infos
|
||||
|
||||
|
||||
class TestGetMusicInfos(unittest.TestCase):
|
||||
|
||||
@patch('musicbrainzngs.search_artists')
|
||||
@patch('musicbrainzngs.search_release_groups')
|
||||
def test_get_music_infos(self, mock_search_release_groups, mock_search_artists):
|
||||
# Arrange
|
||||
artist = 'UltraSinger'
|
||||
title = 'That\'s Rocking!'
|
||||
search = f'{artist} - {title} (UltrStar 2023) FULL HD'
|
||||
|
||||
# Set up mock return values for the MusicBrainz API calls
|
||||
mock_search_artists.return_value = {
|
||||
'artist-list': [
|
||||
{'name': artist}
|
||||
]
|
||||
}
|
||||
|
||||
mock_search_release_groups.return_value = {
|
||||
'release-group-list': [
|
||||
{
|
||||
'title': title,
|
||||
'artist-credit-phrase': artist,
|
||||
'first-release-date': '2023-01-01',
|
||||
'tag-list': [
|
||||
{'name': 'Genre 1'},
|
||||
{'name': 'Genre 2'}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
# Call the function to test
|
||||
title, artist, year, genre = get_music_infos(search)
|
||||
|
||||
# Assert the returned values
|
||||
self.assertEqual(title, 'That\'s Rocking!')
|
||||
self.assertEqual(artist, 'UltraSinger')
|
||||
self.assertEqual(year, '2023-01-01')
|
||||
self.assertEqual(genre, 'Genre 1,Genre 2,')
|
||||
|
||||
@patch('musicbrainzngs.search_artists')
|
||||
@patch('musicbrainzngs.search_release_groups')
|
||||
def test_get_music_infos_when_title_and_artist_are_the_same(self, mock_search_release_groups, mock_search_artists):
|
||||
# Arrange
|
||||
artist = "ArtistIsTitle"
|
||||
title = "ArtistIsTitle"
|
||||
search_not_same = "ArtistIsTitle - ArtistNotTitle"
|
||||
search_is_same = f"{artist} - {title}"
|
||||
|
||||
# Set up mock return values for the MusicBrainz API calls
|
||||
mock_search_artists.return_value = {
|
||||
'artist-list': [
|
||||
{'name': artist}
|
||||
]
|
||||
}
|
||||
|
||||
mock_search_release_groups.return_value = {
|
||||
'release-group-list': [
|
||||
{
|
||||
'title': title,
|
||||
'artist-credit-phrase': artist,
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
# Act search_not_same but musicbrainz returns the same artist and title
|
||||
title, artist, year, genre = get_music_infos(search_not_same)
|
||||
|
||||
# Assert
|
||||
self.assertEqual(title, None)
|
||||
self.assertEqual(artist, None)
|
||||
self.assertEqual(year, None)
|
||||
self.assertEqual(genre, None)
|
||||
|
||||
# Act search_is_same and musicbrainz returns the same artist and title
|
||||
title, artist, year, genre = get_music_infos(search_is_same)
|
||||
|
||||
# Assert
|
||||
self.assertEqual(title, 'ArtistIsTitle')
|
||||
self.assertEqual(artist, 'ArtistIsTitle')
|
||||
self.assertEqual(year, None)
|
||||
self.assertEqual(genre, None)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
+2
-4
@@ -4,10 +4,7 @@ pretty_midi~=0.2.10
|
||||
pydub==0.25.1
|
||||
Levenshtein~=0.21.0
|
||||
scipy~=1.10.1
|
||||
vosk==0.3.44
|
||||
tensorflow~=2.12.0
|
||||
#tensorflow-directml-plugin~=0.4.0.dev230202
|
||||
#cudatoolkit==11.8.0
|
||||
matplotlib~=3.7.1
|
||||
yt_dlp~=2023.3.4
|
||||
numpy~=1.23.5
|
||||
@@ -21,4 +18,5 @@ Pillow~=9.5.0
|
||||
isort==5.12
|
||||
black==23.3
|
||||
pylint==2.17
|
||||
pytest~=7.3.1
|
||||
pytest~=7.3.1
|
||||
musicbrainzngs~=0.7.1
|
||||
+1
-4
@@ -14,14 +14,11 @@ class Settings:
|
||||
audio_chunk_folder_name = "audio-chunks"
|
||||
|
||||
# Whisper
|
||||
transcriber = "whisper" # whisper|vosk
|
||||
transcriber = "whisper" # whisper
|
||||
whisper_model = "large-v2" # Multilingual model tiny|base|small|medium|large-v1|large-v2
|
||||
# English-only model tiny.en|base.en|small.en|medium.en
|
||||
whisper_align_model = None # Model for other languages from huggingface.co e.g -> "gigant/romanian-wav2vec2"
|
||||
|
||||
# Vosk
|
||||
vosk_model_path = "" # "models/vosk-model-small-en-us-0.15"
|
||||
|
||||
# Pitch
|
||||
crepe_model_capacity = "full" # tiny|small|medium|large|full
|
||||
crepe_step_size = 10
|
||||
|
||||
+113
-68
@@ -10,49 +10,49 @@ import Levenshtein
|
||||
import librosa
|
||||
from tqdm import tqdm
|
||||
|
||||
from src.modules import os_helper
|
||||
from src.modules.Audio.denoise import ffmpeg_reduce_noise
|
||||
from src.modules.Audio.separation import separate_audio
|
||||
from src.modules.Audio.vocal_chunks import (
|
||||
from modules import os_helper
|
||||
from modules.Audio.denoise import ffmpeg_reduce_noise
|
||||
from modules.Audio.separation import separate_audio
|
||||
from modules.Audio.vocal_chunks import (
|
||||
export_chunks_from_transcribed_data,
|
||||
export_chunks_from_ultrastar_data,
|
||||
)
|
||||
from src.modules.Audio.silence_processing import remove_silence_from_transcribtion_data
|
||||
from src.modules.csv_handler import export_transcribed_data_to_csv
|
||||
from src.modules.Audio.convert_audio import convert_audio_to_mono_wav, convert_wav_to_mp3
|
||||
from src.modules.Audio.youtube import (
|
||||
from modules.Audio.silence_processing import remove_silence_from_transcribtion_data
|
||||
from modules.csv_handler import export_transcribed_data_to_csv
|
||||
from modules.Audio.convert_audio import convert_audio_to_mono_wav, convert_wav_to_mp3
|
||||
from modules.Audio.youtube import (
|
||||
download_youtube_audio,
|
||||
download_youtube_thumbnail,
|
||||
download_youtube_video,
|
||||
get_youtube_title,
|
||||
)
|
||||
from src.modules.DeviceDetection.device_detection import get_available_device
|
||||
from src.modules.console_colors import (
|
||||
from modules.DeviceDetection.device_detection import get_available_device
|
||||
from modules.console_colors import (
|
||||
ULTRASINGER_HEAD,
|
||||
blue_highlighted,
|
||||
gold_highlighted,
|
||||
light_blue_highlighted,
|
||||
red_highlighted,
|
||||
)
|
||||
from src.modules.Midi import midi_creator
|
||||
from src.modules.Midi.midi_creator import (
|
||||
from modules.Midi import midi_creator
|
||||
from modules.Midi.midi_creator import (
|
||||
convert_frequencies_to_notes,
|
||||
create_midi_notes_from_pitched_data,
|
||||
most_frequent,
|
||||
)
|
||||
from src.modules.Pitcher.pitcher import (
|
||||
from modules.Pitcher.pitcher import (
|
||||
get_frequency_with_high_confidence,
|
||||
get_pitch_with_crepe_file,
|
||||
)
|
||||
from src.modules.Pitcher.pitched_data import PitchedData
|
||||
from src.modules.Speech_Recognition.hyphenation import hyphenation, language_check
|
||||
from src.modules.Speech_Recognition.Vosk import transcribe_with_vosk
|
||||
from src.modules.Speech_Recognition.Whisper import transcribe_with_whisper
|
||||
from src.modules.Ultrastar import ultrastar_score_calculator, ultrastar_writer, ultrastar_converter, ultrastar_parser
|
||||
from src.modules.Ultrastar.ultrastar_txt import UltrastarTxtValue
|
||||
from modules.Pitcher.pitched_data import PitchedData
|
||||
from modules.Speech_Recognition.hyphenation import hyphenation, language_check, create_hyphenator
|
||||
from modules.Speech_Recognition.Whisper import transcribe_with_whisper
|
||||
from modules.Ultrastar import ultrastar_score_calculator, ultrastar_writer, ultrastar_converter, ultrastar_parser
|
||||
from modules.Ultrastar.ultrastar_txt import UltrastarTxtValue
|
||||
from Settings import Settings
|
||||
from src.modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
from src.modules.plot import plot
|
||||
from modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
from modules.plot import plot
|
||||
from modules.musicbrainz_client import get_music_infos
|
||||
|
||||
settings = Settings()
|
||||
|
||||
@@ -144,7 +144,7 @@ def get_bpm_from_data(data, sampling_rate):
|
||||
return wav_tempo[0]
|
||||
|
||||
|
||||
def get_bpm_from_file(wav_file: str):
|
||||
def get_bpm_from_file(wav_file: str) -> float:
|
||||
"""Get real bpm from audio file"""
|
||||
data, sampling_rate = librosa.load(wav_file, sr=None)
|
||||
return get_bpm_from_data(data, sampling_rate)
|
||||
@@ -182,7 +182,8 @@ def print_help() -> None:
|
||||
[mode]
|
||||
## INPUT is audio ##
|
||||
default Creates all
|
||||
|
||||
|
||||
# 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
|
||||
@@ -190,22 +191,27 @@ def print_help() -> None:
|
||||
## INPUT is ultrastar.txt ##
|
||||
default Creates all
|
||||
|
||||
# Single selection is in progress, you currently getting all!
|
||||
(-r repitch Ultrastar.txt (input has to be audio)) # In Progress
|
||||
(-p Check pitch of Ultrastar.txt input) # In Progress
|
||||
(-m Create midi file) # In Progress
|
||||
|
||||
[transcription]
|
||||
--whisper (default) tiny|base|small|medium|large
|
||||
--vosk Needs model
|
||||
# Default is whisper
|
||||
--whisper Multilingual model > tiny|base|small|medium|large-v1|large-v2 >> ((default) is large-v2
|
||||
English-only model > tiny.en|base.en|small.en|medium.en
|
||||
--align_model Use other languages model for Whisper provided from huggingface.co
|
||||
|
||||
[pitcher]
|
||||
# Default is crepe
|
||||
--crepe tiny|small|medium|large|full >> ((default) is full)
|
||||
|
||||
[extra]
|
||||
(-k Keep audio chunks) # In Progress
|
||||
--hyphenation (default) True|False
|
||||
--disable_separation True|False
|
||||
--disable_karaoke True|False
|
||||
|
||||
[pitcher]
|
||||
--crepe (default) tiny|small|medium|large|full
|
||||
--hyphenation True|False >> ((default) is True)
|
||||
--disable_separation True|False >> ((default) is False)
|
||||
--disable_karaoke True|False >> ((default) is False)
|
||||
--create_audio_chunks True|False >> ((default) is False)
|
||||
--plot True|False >> ((default) is False)
|
||||
"""
|
||||
print(help_string)
|
||||
|
||||
@@ -230,9 +236,11 @@ def hyphenate_each_word(language: str, transcribed_data: list[TranscribedData])
|
||||
return None
|
||||
|
||||
sleep(0.1)
|
||||
for i, data in tqdm(enumerate(transcribed_data)):
|
||||
hyphenator = create_hyphenator(lang_region)
|
||||
for i in tqdm(enumerate(transcribed_data)):
|
||||
pos = i[0]
|
||||
hyphenated_word.append(
|
||||
hyphenation(data.word, lang_region)
|
||||
hyphenation(transcribed_data[pos].word, hyphenator)
|
||||
)
|
||||
return hyphenated_word
|
||||
|
||||
@@ -256,6 +264,7 @@ def run() -> None:
|
||||
is_audio = ".txt" not in settings.input_file_path
|
||||
ultrastar_class = None
|
||||
real_bpm = None
|
||||
(title, artist, year, genre) = (None, None, None, None)
|
||||
|
||||
if not is_audio: # Parse Ultrastar txt
|
||||
print(
|
||||
@@ -276,6 +285,7 @@ def run() -> None:
|
||||
basename_without_ext,
|
||||
song_output,
|
||||
ultrastar_audio_input_path,
|
||||
(title, artist, year, genre)
|
||||
) = download_from_youtube()
|
||||
else: # Audio File
|
||||
print(
|
||||
@@ -285,6 +295,7 @@ def run() -> None:
|
||||
basename_without_ext,
|
||||
song_output,
|
||||
ultrastar_audio_input_path,
|
||||
(title, artist, year, genre)
|
||||
) = infos_from_audio_input_file()
|
||||
|
||||
cache_path = os.path.join(song_output, "cache")
|
||||
@@ -351,6 +362,10 @@ def run() -> None:
|
||||
ultrastar_audio_input_path,
|
||||
ultrastar_note_numbers,
|
||||
language,
|
||||
title,
|
||||
artist,
|
||||
year,
|
||||
genre
|
||||
)
|
||||
else:
|
||||
ultrastar_file_output = create_ultrastar_txt_from_ultrastar_data(
|
||||
@@ -369,7 +384,7 @@ def run() -> None:
|
||||
|
||||
# Midi
|
||||
if settings.create_midi:
|
||||
create_midi_file(is_audio, real_bpm, song_output, ultrastar_class)
|
||||
create_midi_file(real_bpm, song_output, ultrastar_class, basename_without_ext)
|
||||
|
||||
# Print Support
|
||||
print_support()
|
||||
@@ -401,12 +416,8 @@ def transcribe_audio() -> (str, list[TranscribedData]):
|
||||
device = "cpu" if settings.force_whisper_cpu else settings.device
|
||||
transcribed_data, language = transcribe_with_whisper(
|
||||
settings.mono_audio_path, settings.whisper_model, device, settings.whisper_align_model)
|
||||
else: # vosk
|
||||
transcribed_data = transcribe_with_vosk(
|
||||
settings.mono_audio_path, settings.vosk_model_path
|
||||
)
|
||||
# todo: make language selectable
|
||||
language = "en"
|
||||
else:
|
||||
raise NotImplementedError
|
||||
return language, transcribed_data
|
||||
|
||||
|
||||
@@ -501,6 +512,10 @@ def create_ultrastar_txt_from_automation(
|
||||
ultrastar_audio_input_path: str,
|
||||
ultrastar_note_numbers: list[int],
|
||||
language: str,
|
||||
title: str,
|
||||
artist: str,
|
||||
year: str,
|
||||
genre: str
|
||||
):
|
||||
"""Create Ultrastar txt from automation"""
|
||||
ultrastar_header = UltrastarTxtValue()
|
||||
@@ -516,6 +531,16 @@ def create_ultrastar_txt_from_automation(
|
||||
else None
|
||||
)
|
||||
|
||||
# Additional data
|
||||
if title is not None:
|
||||
ultrastar_header.title = title
|
||||
if artist is not None:
|
||||
ultrastar_header.artist = artist
|
||||
if year is not None:
|
||||
ultrastar_header.year = year
|
||||
if genre is not None:
|
||||
ultrastar_header.genre = genre
|
||||
|
||||
real_bpm = get_bpm_from_file(ultrastar_audio_input_path)
|
||||
ultrastar_file_output = os.path.join(
|
||||
song_output, basename_without_ext + ".txt"
|
||||
@@ -546,16 +571,37 @@ def create_ultrastar_txt_from_automation(
|
||||
return real_bpm, ultrastar_file_output
|
||||
|
||||
|
||||
def infos_from_audio_input_file() -> tuple[str, str, str]:
|
||||
def infos_from_audio_input_file() -> tuple[str, str, str, tuple[str, str, str, str]]:
|
||||
"""Infos from audio input file"""
|
||||
basename = os.path.basename(settings.input_file_path)
|
||||
basename_without_ext = os.path.splitext(basename)[0]
|
||||
|
||||
artist, title = None, None
|
||||
if " - " in basename_without_ext:
|
||||
artist, title = basename_without_ext.split(" - ", 1)
|
||||
search_string = f"{artist} - {title}"
|
||||
else:
|
||||
search_string = basename_without_ext
|
||||
|
||||
# Get additional data for song
|
||||
(title_info, artist_info, year_info, genre_info) = get_music_infos(search_string)
|
||||
|
||||
if title_info is not None:
|
||||
title = title_info
|
||||
artist = artist_info
|
||||
|
||||
if artist is not None and title is not None:
|
||||
basename_without_ext = f"{artist} - {title}"
|
||||
extension = os.path.splitext(basename)[1]
|
||||
basename = f"{basename_without_ext}{extension}"
|
||||
|
||||
song_output = os.path.join(settings.output_file_path, basename_without_ext)
|
||||
song_output = get_unused_song_output_dir(song_output)
|
||||
os_helper.create_folder(song_output)
|
||||
os_helper.copy(settings.input_file_path, song_output)
|
||||
os_helper.rename(os.path.join(song_output, os.path.basename(settings.input_file_path)), os.path.join(song_output, basename))
|
||||
ultrastar_audio_input_path = os.path.join(song_output, basename)
|
||||
return basename_without_ext, song_output, ultrastar_audio_input_path
|
||||
return basename_without_ext, song_output, ultrastar_audio_input_path, (title, artist, year_info, genre_info)
|
||||
|
||||
|
||||
FILENAME_REPLACEMENTS = (('?:"', ""), ("<", "("), (">", ")"), ("/\\|*", "-"))
|
||||
@@ -571,10 +617,18 @@ def sanitize_filename(fname: str) -> str:
|
||||
return fname
|
||||
|
||||
|
||||
def download_from_youtube() -> tuple[str, str, str]:
|
||||
def download_from_youtube() -> tuple[str, str, str, tuple[str, str, str, str]]:
|
||||
"""Download from YouTube"""
|
||||
title = get_youtube_title(settings.input_file_path)
|
||||
basename_without_ext = sanitize_filename(title)
|
||||
(artist, title) = get_youtube_title(settings.input_file_path)
|
||||
|
||||
# Get additional data for song
|
||||
(title_info, artist_info, year_info, genre_info) = get_music_infos(f"{artist} - {title}")
|
||||
|
||||
if title_info is not None:
|
||||
title = title_info
|
||||
artist = artist_info
|
||||
|
||||
basename_without_ext = sanitize_filename(f"{artist} - {title}")
|
||||
basename = basename_without_ext + ".mp3"
|
||||
song_output = os.path.join(settings.output_file_path, basename_without_ext)
|
||||
song_output = get_unused_song_output_dir(song_output)
|
||||
@@ -589,7 +643,7 @@ def download_from_youtube() -> tuple[str, str, str]:
|
||||
settings.input_file_path, basename_without_ext, song_output
|
||||
)
|
||||
ultrastar_audio_input_path = os.path.join(song_output, basename)
|
||||
return basename_without_ext, song_output, ultrastar_audio_input_path
|
||||
return basename_without_ext, song_output, ultrastar_audio_input_path, (title, artist, year_info, genre_info)
|
||||
|
||||
|
||||
def parse_ultrastar_txt() -> tuple[str, float, str, str, UltrastarTxtValue]:
|
||||
@@ -619,27 +673,22 @@ def parse_ultrastar_txt() -> tuple[str, float, str, str, UltrastarTxtValue]:
|
||||
)
|
||||
|
||||
|
||||
def create_midi_file(is_audio: bool, real_bpm: float, song_output: str, ultrastar_class: UltrastarTxtValue) -> None:
|
||||
def create_midi_file(real_bpm: float,
|
||||
song_output: str,
|
||||
ultrastar_class: UltrastarTxtValue,
|
||||
basename_without_ext: str) -> None:
|
||||
"""Create midi file"""
|
||||
print(
|
||||
f"{ULTRASINGER_HEAD} Creating Midi with {blue_highlighted('pretty_midi')}"
|
||||
)
|
||||
if is_audio:
|
||||
voice_instrument = [
|
||||
midi_creator.convert_ultrastar_to_midi_instrument(ultrastar_class)
|
||||
]
|
||||
midi_output = os.path.join(song_output, ultrastar_class.title + ".mid")
|
||||
midi_creator.instruments_to_midi(
|
||||
voice_instrument, real_bpm, midi_output
|
||||
)
|
||||
else:
|
||||
voice_instrument = [
|
||||
midi_creator.convert_ultrastar_to_midi_instrument(ultrastar_class)
|
||||
]
|
||||
midi_output = os.path.join(song_output, ultrastar_class.title + ".mid")
|
||||
midi_creator.instruments_to_midi(
|
||||
voice_instrument, real_bpm, midi_output
|
||||
)
|
||||
|
||||
voice_instrument = [
|
||||
midi_creator.convert_ultrastar_to_midi_instrument(ultrastar_class)
|
||||
]
|
||||
midi_output = os.path.join(song_output, f"{basename_without_ext}.mid")
|
||||
midi_creator.instruments_to_midi(
|
||||
voice_instrument, real_bpm, midi_output
|
||||
)
|
||||
|
||||
|
||||
def pitch_audio(is_audio: bool, transcribed_data: list[TranscribedData], ultrastar_class: UltrastarTxtValue) -> tuple[
|
||||
@@ -731,9 +780,6 @@ def init_settings(argv: list[str]) -> None:
|
||||
settings.whisper_model = arg
|
||||
elif opt in ("--align_model"):
|
||||
settings.whisper_align_model = arg
|
||||
elif opt in ("--vosk"):
|
||||
settings.transcriber = "vosk"
|
||||
settings.vosk_model_path = arg
|
||||
elif opt in ("--crepe"):
|
||||
settings.crepe_model_capacity = arg
|
||||
elif opt in ("--plot"):
|
||||
@@ -765,7 +811,6 @@ def arg_options():
|
||||
"ifile=",
|
||||
"ofile=",
|
||||
"crepe=",
|
||||
"vosk=",
|
||||
"whisper=",
|
||||
"align_model=",
|
||||
"plot=",
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
from pydub import AudioSegment
|
||||
|
||||
from src.modules.console_colors import ULTRASINGER_HEAD
|
||||
from modules.console_colors import ULTRASINGER_HEAD
|
||||
|
||||
|
||||
def convert_audio_to_mono_wav(input_file: str, output_file: str) -> None:
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
import ffmpeg
|
||||
|
||||
from src.modules.console_colors import ULTRASINGER_HEAD, blue_highlighted
|
||||
from modules.console_colors import ULTRASINGER_HEAD, blue_highlighted
|
||||
|
||||
|
||||
def ffmpeg_reduce_noise(input_file_path: str, output_file: str) -> None:
|
||||
|
||||
@@ -2,12 +2,12 @@
|
||||
|
||||
import subprocess
|
||||
|
||||
from src.modules.console_colors import (
|
||||
from modules.console_colors import (
|
||||
ULTRASINGER_HEAD,
|
||||
blue_highlighted,
|
||||
red_highlighted,
|
||||
)
|
||||
from src.modules.os_helper import current_executor_path, move, path_join
|
||||
from modules.os_helper import current_executor_path, move, path_join
|
||||
|
||||
|
||||
def separate_audio(input_file_path: str, output_file: str, device="cpu") -> None:
|
||||
|
||||
@@ -2,8 +2,8 @@
|
||||
|
||||
import librosa
|
||||
|
||||
from src.modules.console_colors import ULTRASINGER_HEAD
|
||||
from src.modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
from modules.console_colors import ULTRASINGER_HEAD
|
||||
from modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
|
||||
|
||||
def remove_silence_from_transcribtion_data(audio_path: str, transcribed_data: list[TranscribedData]) -> list[TranscribedData]:
|
||||
|
||||
@@ -4,13 +4,13 @@ import os
|
||||
import re
|
||||
import wave
|
||||
|
||||
from src.modules.console_colors import ULTRASINGER_HEAD
|
||||
from src.modules.os_helper import create_folder
|
||||
from src.modules.Ultrastar.ultrastar_converter import (
|
||||
from modules.console_colors import ULTRASINGER_HEAD
|
||||
from modules.os_helper import create_folder
|
||||
from modules.Ultrastar.ultrastar_converter import (
|
||||
get_end_time_from_ultrastar,
|
||||
get_start_time_from_ultrastar,
|
||||
)
|
||||
from src.modules.Ultrastar.ultrastar_txt import UltrastarTxtValue
|
||||
from modules.Ultrastar.ultrastar_txt import UltrastarTxtValue
|
||||
|
||||
|
||||
class AudioManipulation:
|
||||
|
||||
@@ -6,10 +6,10 @@ import os
|
||||
import yt_dlp
|
||||
from PIL import Image
|
||||
|
||||
from src.modules.console_colors import ULTRASINGER_HEAD
|
||||
from modules.console_colors import ULTRASINGER_HEAD
|
||||
from modules.Image.image_helper import crop_image_to_square
|
||||
|
||||
|
||||
def get_youtube_title(url: str) -> str:
|
||||
def get_youtube_title(url: str) -> tuple[str, str]:
|
||||
"""Get the title of the YouTube video"""
|
||||
|
||||
ydl_opts = {}
|
||||
@@ -18,7 +18,11 @@ def get_youtube_title(url: str) -> str:
|
||||
url, download=False # We just want to extract the info
|
||||
)
|
||||
|
||||
return result["title"]
|
||||
if "artist" in result:
|
||||
return result["artist"], result["track"]
|
||||
if "-" in result["title"]:
|
||||
return result["title"].split("-")[0], result["title"].split("-")[1]
|
||||
return result["channel"], result["title"]
|
||||
|
||||
|
||||
def download_youtube_audio(url: str, clear_filename: str, output_path: str):
|
||||
@@ -58,9 +62,9 @@ def download_and_convert_thumbnail(ydl_opts, url: str, clear_filename: str, outp
|
||||
response = ydl.urlopen(thumbnail_url)
|
||||
image_data = response.read()
|
||||
image = Image.open(io.BytesIO(image_data))
|
||||
image.save(
|
||||
os.path.join(output_path, clear_filename + " [CO].jpg"), "JPEG"
|
||||
)
|
||||
image_path = os.path.join(output_path, clear_filename + " [CO].jpg")
|
||||
image.save(image_path, "JPEG")
|
||||
crop_image_to_square(image_path)
|
||||
|
||||
|
||||
def download_youtube_video(url: str, clear_filename: str, output_path: str) -> None:
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
import torch
|
||||
|
||||
from src.modules.console_colors import ULTRASINGER_HEAD, red_highlighted
|
||||
from modules.console_colors import ULTRASINGER_HEAD, red_highlighted
|
||||
|
||||
|
||||
def get_available_device() -> str:
|
||||
|
||||
@@ -0,0 +1,18 @@
|
||||
from PIL import Image
|
||||
|
||||
|
||||
def crop_image_to_square(image_path):
|
||||
image = Image.open(image_path)
|
||||
width, height = image.size
|
||||
size = min(width, height)
|
||||
|
||||
# Calculate the coordinates for the crop
|
||||
left = (width - size) // 2
|
||||
top = (height - size) // 2
|
||||
right = left + size
|
||||
bottom = top + size
|
||||
|
||||
cropped_image = image.crop((left, top, right, bottom))
|
||||
|
||||
# Override the original image with the cropped version
|
||||
cropped_image.save(image_path)
|
||||
@@ -7,18 +7,18 @@ import librosa
|
||||
import numpy as np
|
||||
import pretty_midi
|
||||
|
||||
from src.modules.Pitcher.pitcher import get_frequency_with_high_confidence
|
||||
from src.modules.Ultrastar.ultrastar_converter import (
|
||||
from modules.Pitcher.pitcher import get_frequency_with_high_confidence
|
||||
from modules.Ultrastar.ultrastar_converter import (
|
||||
get_end_time_from_ultrastar,
|
||||
get_start_time_from_ultrastar,
|
||||
ultrastar_note_to_midi_note,
|
||||
)
|
||||
from src.modules.console_colors import (
|
||||
from modules.console_colors import (
|
||||
ULTRASINGER_HEAD,
|
||||
red_highlighted,
|
||||
)
|
||||
from src.modules.Ultrastar.ultrastar_txt import UltrastarTxtValue
|
||||
from src.modules.Pitcher.pitched_data import PitchedData
|
||||
from modules.Ultrastar.ultrastar_txt import UltrastarTxtValue
|
||||
from modules.Pitcher.pitched_data import PitchedData
|
||||
|
||||
|
||||
def convert_ultrastar_to_midi_instrument(ultrastar_class: UltrastarTxtValue) -> object:
|
||||
|
||||
@@ -3,12 +3,12 @@
|
||||
import crepe
|
||||
from scipy.io import wavfile
|
||||
|
||||
from src.modules.console_colors import (
|
||||
from modules.console_colors import (
|
||||
ULTRASINGER_HEAD,
|
||||
blue_highlighted,
|
||||
red_highlighted,
|
||||
)
|
||||
from src.modules.Pitcher.pitched_data import PitchedData
|
||||
from modules.Pitcher.pitched_data import PitchedData
|
||||
|
||||
|
||||
def get_pitch_with_crepe_file(filename: str, step_size: int, model_capacity: str) -> PitchedData:
|
||||
|
||||
@@ -1,65 +0,0 @@
|
||||
"""Vosk speech recognition module."""
|
||||
|
||||
import json
|
||||
import wave
|
||||
|
||||
from vosk import KaldiRecognizer, Model
|
||||
|
||||
from src.modules.console_colors import ULTRASINGER_HEAD
|
||||
from src.modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
|
||||
# todo: Rename to Transcoder?
|
||||
|
||||
|
||||
def transcribe_with_vosk(audio_filename: str, model_path: str) -> list[TranscribedData]:
|
||||
"""Transcribe with vosk"""
|
||||
# Code from here: https://towardsdatascience.com/speech-recognition-with-timestamps-934ede4234b2
|
||||
print(
|
||||
f"{ULTRASINGER_HEAD} Transcribing {audio_filename} with vosk and model {model_path}"
|
||||
)
|
||||
|
||||
model = Model(model_path)
|
||||
wave_file = wave.open(audio_filename, "rb")
|
||||
recognizer = KaldiRecognizer(model, wave_file.getframerate())
|
||||
|
||||
recognizer.SetWords(True)
|
||||
|
||||
# get the list of JSON dictionaries
|
||||
results = []
|
||||
# recognize speech using vosk model
|
||||
while True:
|
||||
data = wave_file.readframes(4000)
|
||||
if len(data) == 0:
|
||||
break
|
||||
if recognizer.AcceptWaveform(data):
|
||||
part_result = json.loads(recognizer.Result())
|
||||
results.append(part_result)
|
||||
wave_file.close() # close audiofile
|
||||
part_result = json.loads(recognizer.FinalResult())
|
||||
results.append(part_result)
|
||||
|
||||
# convert list of JSON dictionaries to list of 'Word' objects
|
||||
transcribed_data = []
|
||||
for sentence in results:
|
||||
if len(sentence) == 1:
|
||||
# sometimes there are bugs in recognition
|
||||
# and it returns an empty dictionary
|
||||
# {'text': ''}
|
||||
continue
|
||||
for obj in sentence["result"]:
|
||||
vtd = TranscribedData(obj) # create custom Word object
|
||||
vtd.word = vtd.word + " "
|
||||
transcribed_data.append(vtd) # and add it to list
|
||||
|
||||
# Todo: remove silent part from each word
|
||||
|
||||
# output to the screen
|
||||
# todo: progress?
|
||||
# for word in vosk_transcribed_data:
|
||||
# print(word.to_string())
|
||||
|
||||
return transcribed_data
|
||||
|
||||
|
||||
class SpeechToText:
|
||||
"""Docstring"""
|
||||
@@ -3,15 +3,16 @@
|
||||
import whisperx
|
||||
import sys
|
||||
|
||||
from src.modules.console_colors import (
|
||||
from modules.console_colors import (
|
||||
ULTRASINGER_HEAD,
|
||||
blue_highlighted,
|
||||
red_highlighted,
|
||||
)
|
||||
from src.modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
from modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
|
||||
|
||||
def transcribe_with_whisper(audio_path: str, model: str, device="cpu", model_name: str = None) -> (list[TranscribedData], str):
|
||||
def transcribe_with_whisper(audio_path: str, model: str, device="cpu", model_name: str = None) -> (
|
||||
list[TranscribedData], str):
|
||||
"""Transcribe with whisper"""
|
||||
|
||||
print(
|
||||
@@ -25,7 +26,6 @@ def transcribe_with_whisper(audio_path: str, model: str, device="cpu", model_nam
|
||||
"float16" if device == "cuda" else "int8"
|
||||
) # change to "int8" if low on GPU mem (may reduce accuracy)
|
||||
|
||||
# transcribe with original whisper
|
||||
loaded_whisper_model = whisperx.load_model(
|
||||
model, device=device, compute_type=compute_type
|
||||
)
|
||||
@@ -57,8 +57,13 @@ def transcribe_with_whisper(audio_path: str, model: str, device="cpu", model_nam
|
||||
return_char_alignments=False,
|
||||
)
|
||||
|
||||
transcribed_data = []
|
||||
transcribed_data = convert_to_transcribed_data(result_aligned)
|
||||
|
||||
return transcribed_data, language
|
||||
|
||||
|
||||
def convert_to_transcribed_data(result_aligned):
|
||||
transcribed_data = []
|
||||
for segment in result_aligned["segments"]:
|
||||
for obj in segment["words"]:
|
||||
if len(obj) < 4:
|
||||
@@ -67,7 +72,6 @@ def transcribe_with_whisper(audio_path: str, model: str, device="cpu", model_nam
|
||||
)
|
||||
continue
|
||||
vtd = TranscribedData(obj) # create custom Word object
|
||||
vtd.word = vtd.word + " "
|
||||
vtd.word = vtd.word + " " # add space to end of word
|
||||
transcribed_data.append(vtd) # and add it to list
|
||||
|
||||
return transcribed_data, language
|
||||
return transcribed_data
|
||||
@@ -4,7 +4,7 @@ import string
|
||||
|
||||
from hyphen import Hyphenator, dictools
|
||||
|
||||
from src.modules.console_colors import (
|
||||
from modules.console_colors import (
|
||||
ULTRASINGER_HEAD,
|
||||
blue_highlighted,
|
||||
)
|
||||
@@ -36,20 +36,66 @@ def contains_punctuation(word: str) -> bool:
|
||||
return any(elem in word for elem in string.punctuation)
|
||||
|
||||
|
||||
def hyphenation(word: str, lang_region: str) -> list[str] | None:
|
||||
def clean_word(word: str):
|
||||
"""Remove punctuation from word"""
|
||||
cleaned_string = ""
|
||||
removed_indices = []
|
||||
removed_symbols = []
|
||||
for i, char in enumerate(word):
|
||||
if char not in string.punctuation and char not in " ":
|
||||
cleaned_string += char
|
||||
else:
|
||||
removed_indices.append(i)
|
||||
removed_symbols.append(char)
|
||||
return cleaned_string, removed_indices, removed_symbols
|
||||
|
||||
|
||||
def insert_removed_symbols(separated_array, removed_indices, symbols):
|
||||
"""Insert symbols into the syllables"""
|
||||
result = []
|
||||
symbol_index = 0
|
||||
i = 0
|
||||
|
||||
# Add removed symbols to the syllables
|
||||
for syllable in separated_array:
|
||||
tmp = ""
|
||||
for char in syllable:
|
||||
if i in removed_indices:
|
||||
tmp += symbols[symbol_index]
|
||||
symbol_index += 1
|
||||
i += 1
|
||||
tmp += char
|
||||
i += 1
|
||||
result.append(tmp)
|
||||
|
||||
# Add remaining symbols to the last syllable
|
||||
if symbol_index < len(symbols):
|
||||
tmp = result[-1]
|
||||
for i in range(symbol_index, len(symbols)):
|
||||
tmp += symbols[i]
|
||||
result[-1] = tmp
|
||||
|
||||
return result
|
||||
|
||||
|
||||
def create_hyphenator(lang_region: str) -> Hyphenator:
|
||||
"""Create hyphenator"""
|
||||
hyphenator = Hyphenator(lang_region)
|
||||
return hyphenator
|
||||
|
||||
|
||||
def hyphenation(word: str, hyphenator: Hyphenator) -> list[str] | None:
|
||||
"""Hyphenate word"""
|
||||
|
||||
if contains_punctuation(word):
|
||||
return None
|
||||
|
||||
hyphenator = Hyphenator(lang_region)
|
||||
syllabus = hyphenator.syllables(word)
|
||||
cleaned_string, removed_indices, removed_symbols = clean_word(word)
|
||||
syllabus = hyphenator.syllables(cleaned_string)
|
||||
|
||||
length = len(syllabus)
|
||||
if length > 1:
|
||||
hyphen = []
|
||||
for i in range(length):
|
||||
hyphen.append(syllabus[i])
|
||||
hyphen = insert_removed_symbols(hyphen, removed_indices, removed_symbols)
|
||||
else:
|
||||
hyphen = None
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ import speech_recognition as sr
|
||||
from pydub import AudioSegment
|
||||
from pydub.silence import split_on_silence
|
||||
|
||||
from src.modules.console_colors import ULTRASINGER_HEAD
|
||||
from modules.console_colors import ULTRASINGER_HEAD
|
||||
|
||||
# todo: Code from here: https://www.thepythoncode.com/article/using-speech-recognition-to-convert-speech-to-text-python
|
||||
|
||||
|
||||
@@ -1,17 +1,17 @@
|
||||
"""Ultrastar Converter"""
|
||||
|
||||
from src.modules.Ultrastar.ultrastar_txt import UltrastarTxtValue
|
||||
from modules.Ultrastar.ultrastar_txt import UltrastarTxtValue
|
||||
|
||||
def real_bpm_to_ultrastar_bpm(real_bpm: float) -> float:
|
||||
"""Converts real BPM to UltraStar BPM"""
|
||||
# The UltraStar BPM info is a fifth beat of the real BPM
|
||||
# The UltraStar BPM info is a fourth beat of the real BPM
|
||||
ultrastar_bpm = real_bpm / 4
|
||||
return ultrastar_bpm
|
||||
|
||||
|
||||
def ultrastar_bpm_to_real_bpm(ultrastar_bpm: float) -> float:
|
||||
"""Converts UltraStar BPM to real BPM"""
|
||||
# The UltraStar BPM info is a fifth beat of the real BPM
|
||||
# The UltraStar BPM info is a fourth beat of the real BPM
|
||||
bpm = ultrastar_bpm * 4
|
||||
return bpm
|
||||
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
"""Ultrastar txt parser"""
|
||||
|
||||
from src.modules.console_colors import ULTRASINGER_HEAD
|
||||
from src.modules.Ultrastar.ultrastar_converter import (
|
||||
from modules.console_colors import ULTRASINGER_HEAD
|
||||
from modules.Ultrastar.ultrastar_converter import (
|
||||
get_end_time_from_ultrastar,
|
||||
get_start_time_from_ultrastar,
|
||||
)
|
||||
from src.modules.Ultrastar.ultrastar_txt import UltrastarTxtValue, UltrastarTxtTag, UltrastarTxtNoteTypeTag, FILE_ENCODING
|
||||
from modules.Ultrastar.ultrastar_txt import UltrastarTxtValue, UltrastarTxtTag, UltrastarTxtNoteTypeTag, FILE_ENCODING
|
||||
|
||||
def parse_ultrastar_txt(input_file: str) -> UltrastarTxtValue:
|
||||
"""Parse ultrastar txt file to UltrastarTxt class"""
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
import librosa
|
||||
|
||||
from src.modules.console_colors import (
|
||||
from modules.console_colors import (
|
||||
ULTRASINGER_HEAD,
|
||||
blue_highlighted,
|
||||
cyan_highlighted,
|
||||
@@ -10,14 +10,14 @@ from src.modules.console_colors import (
|
||||
light_blue_highlighted,
|
||||
underlined,
|
||||
)
|
||||
from src.modules.Midi.midi_creator import create_midi_note_from_pitched_data
|
||||
from src.modules.Ultrastar.ultrastar_converter import (
|
||||
from modules.Midi.midi_creator import create_midi_note_from_pitched_data
|
||||
from modules.Ultrastar.ultrastar_converter import (
|
||||
get_end_time_from_ultrastar,
|
||||
get_start_time_from_ultrastar,
|
||||
ultrastar_note_to_midi_note,
|
||||
)
|
||||
from src.modules.Ultrastar.ultrastar_txt import UltrastarTxtValue
|
||||
from src.modules.Pitcher.pitched_data import PitchedData
|
||||
from modules.Ultrastar.ultrastar_txt import UltrastarTxtValue
|
||||
from modules.Pitcher.pitched_data import PitchedData
|
||||
|
||||
MAX_SONG_SCORE = 10000
|
||||
MAX_SONG_LINE_BONUS = 1000
|
||||
@@ -107,7 +107,7 @@ def calculate_score(pitched_data: PitchedData, ultrastar_class: UltrastarTxtValu
|
||||
start_time = get_start_time_from_ultrastar(ultrastar_class, pos)
|
||||
end_time = get_end_time_from_ultrastar(ultrastar_class, pos)
|
||||
duration = end_time - start_time
|
||||
step_size = 0.01 # todo: should be beat length ?
|
||||
step_size = 0.09 # Todo: Whats is the step size of the game? Its not 1/bps -> one beat in seconds s = 60/bpm
|
||||
parts = int(duration / step_size)
|
||||
parts = 1 if parts == 0 else parts
|
||||
|
||||
@@ -122,6 +122,8 @@ def calculate_score(pitched_data: PitchedData, ultrastar_class: UltrastarTxtValu
|
||||
for part in range(parts):
|
||||
start = start_time + step_size * part
|
||||
end = start + step_size
|
||||
if end_time < end or part == parts - 1:
|
||||
end = end_time
|
||||
pitch_note = create_midi_note_from_pitched_data(
|
||||
start, end, pitched_data
|
||||
)
|
||||
|
||||
@@ -59,6 +59,8 @@ class UltrastarTxtValue:
|
||||
|
||||
artist = ""
|
||||
title = ""
|
||||
year = None
|
||||
genre = ""
|
||||
mp3 = ""
|
||||
video = None
|
||||
gap = ""
|
||||
|
||||
@@ -4,14 +4,15 @@ import re
|
||||
|
||||
import langcodes
|
||||
|
||||
from src.modules.console_colors import ULTRASINGER_HEAD
|
||||
from src.modules.Ultrastar.ultrastar_converter import (
|
||||
from modules.console_colors import ULTRASINGER_HEAD
|
||||
from modules.Ultrastar.ultrastar_converter import (
|
||||
real_bpm_to_ultrastar_bpm,
|
||||
second_to_beat,
|
||||
)
|
||||
from src.modules.Ultrastar.ultrastar_txt import UltrastarTxtValue, UltrastarTxtTag, UltrastarTxtNoteTypeTag, FILE_ENCODING
|
||||
from src.modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
from src.modules.Ultrastar.ultrastar_score_calculator import Score
|
||||
from modules.Ultrastar.ultrastar_txt import UltrastarTxtValue, UltrastarTxtTag, UltrastarTxtNoteTypeTag, \
|
||||
FILE_ENCODING
|
||||
from modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
from modules.Ultrastar.ultrastar_score_calculator import Score
|
||||
|
||||
|
||||
def get_multiplier(real_bpm: float) -> int:
|
||||
@@ -47,27 +48,29 @@ def create_ultrastar_txt_from_automation(
|
||||
f"{ULTRASINGER_HEAD} Creating {ultrastar_file_output} from transcription."
|
||||
)
|
||||
|
||||
real_bpm = real_bpm_to_ultrastar_bpm(bpm)
|
||||
multiplication = get_multiplier(real_bpm)
|
||||
ultrastar_bpm = real_bpm * get_multiplier(real_bpm)
|
||||
ultrastar_bpm = real_bpm_to_ultrastar_bpm(bpm)
|
||||
multiplication = get_multiplier(ultrastar_bpm)
|
||||
ultrastar_bpm = ultrastar_bpm * get_multiplier(ultrastar_bpm)
|
||||
|
||||
with open(ultrastar_file_output, "w", encoding=FILE_ENCODING) as file:
|
||||
gap = transcribed_data[0].start
|
||||
|
||||
file.write(f"#{UltrastarTxtTag.ARTIST}:{ultrastar_class.artist}\n")
|
||||
file.write(f"#{UltrastarTxtTag.TITLE}:{ultrastar_class.title}\n")
|
||||
file.write(f"#{UltrastarTxtTag.CREATOR}:{ultrastar_class.creator}\n")
|
||||
file.write(f"#{UltrastarTxtTag.FIXER}:{ultrastar_class.fixer}\n")
|
||||
if ultrastar_class.year is not None:
|
||||
file.write(f"#{UltrastarTxtTag.YEAR}:{ultrastar_class.year}\n")
|
||||
if ultrastar_class.language is not None:
|
||||
file.write(
|
||||
f"#{UltrastarTxtTag.LANGUAGE}:{get_language_name(ultrastar_class.language)}\n"
|
||||
)
|
||||
file.write(f"#{UltrastarTxtTag.LANGUAGE}:{get_language_name(ultrastar_class.language)}\n")
|
||||
if ultrastar_class.genre:
|
||||
file.write(f"#{UltrastarTxtTag.GENRE}:{ultrastar_class.genre}\n")
|
||||
if ultrastar_class.cover is not None:
|
||||
file.write(f"#{UltrastarTxtTag.COVER}:{ultrastar_class.cover}\n")
|
||||
file.write(f"#{UltrastarTxtTag.MP3}:{ultrastar_class.mp3}\n")
|
||||
file.write(f"#{UltrastarTxtTag.VIDEO}:{ultrastar_class.video}\n")
|
||||
file.write(f"#{UltrastarTxtTag.BPM}:{round(ultrastar_bpm, 2)}\n") # not the real BPM!
|
||||
file.write(f"#{UltrastarTxtTag.GAP}:{int(gap * 1000)}\n")
|
||||
file.write(f"#{UltrastarTxtTag.CREATOR}:{ultrastar_class.creator}\n")
|
||||
file.write(f"#{UltrastarTxtTag.FIXER}:{ultrastar_class.fixer}\n")
|
||||
file.write(f"#{UltrastarTxtTag.COMMENT}:{ultrastar_class.comment}\n")
|
||||
|
||||
# Write the singing part
|
||||
@@ -90,12 +93,12 @@ def create_ultrastar_txt_from_automation(
|
||||
# 'n2' duration at real beat
|
||||
# 'n3' pitch where 0 == C4
|
||||
# 'w' lyric
|
||||
file.write(f"{UltrastarTxtNoteTypeTag.NORMAL} ")
|
||||
file.write(str(start_beat) + " ")
|
||||
file.write(str(duration) + " ")
|
||||
file.write(str(note_numbers[i]) + " ")
|
||||
file.write(data.word)
|
||||
file.write("\n")
|
||||
line = f"{UltrastarTxtNoteTypeTag.NORMAL} " \
|
||||
f"{str(start_beat)} " \
|
||||
f"{str(duration)} " \
|
||||
f"{str(note_numbers[i])} " \
|
||||
f"{data.word}\n"
|
||||
file.write(line)
|
||||
|
||||
# detect silence between words
|
||||
if i < len(transcribed_data) - 1:
|
||||
@@ -109,13 +112,13 @@ def create_ultrastar_txt_from_automation(
|
||||
# - 10
|
||||
# '-' end of current sing part
|
||||
# 'n1' show next at time in real beat
|
||||
file.write(f"{UltrastarTxtTag.LINEBREAK} ")
|
||||
show_next = (
|
||||
second_to_beat(data.end - gap, bpm)
|
||||
* multiplication
|
||||
)
|
||||
file.write(str(round(show_next)))
|
||||
file.write("\n")
|
||||
linebreak = f"{UltrastarTxtTag.LINEBREAK} " \
|
||||
f"{str(round(show_next))}\n"
|
||||
file.write(linebreak)
|
||||
file.write(f"{UltrastarTxtTag.FILE_END}")
|
||||
|
||||
|
||||
|
||||
@@ -2,8 +2,8 @@
|
||||
|
||||
import csv
|
||||
|
||||
from src.modules.console_colors import ULTRASINGER_HEAD
|
||||
from src.modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
from modules.console_colors import ULTRASINGER_HEAD
|
||||
from modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
|
||||
|
||||
def export_transcribed_data_to_csv(transcribed_data: list[TranscribedData], filename: str) -> None:
|
||||
|
||||
@@ -0,0 +1,56 @@
|
||||
import musicbrainzngs
|
||||
import string
|
||||
from modules.console_colors import ULTRASINGER_HEAD, blue_highlighted, red_highlighted
|
||||
|
||||
|
||||
def get_music_infos(search_string: str) -> tuple[str, str, str, str]:
|
||||
print(f"{ULTRASINGER_HEAD} Searching song in {blue_highlighted('musicbrainz')}")
|
||||
# https://python-musicbrainzngs.readthedocs.io/en/v0.7.1/usage/#searching
|
||||
|
||||
musicbrainzngs.set_useragent("UltraSinger", "0.1", "https://github.com/rakuri255/UltraSinger")
|
||||
|
||||
# search for artist and titel to get release on the first place
|
||||
artists = musicbrainzngs.search_artists(search_string)
|
||||
artist = artists['artist-list'][0]['name']
|
||||
release_groups = musicbrainzngs.search_release_groups(search_string, artist=artist)
|
||||
release = release_groups['release-group-list'][0]
|
||||
|
||||
if 'artist-credit-phrase' in release:
|
||||
artist = release['artist-credit-phrase']
|
||||
|
||||
title = None
|
||||
if 'title' in release:
|
||||
clean_search_string = search_string.translate(str.maketrans('', '', string.punctuation)).lower()
|
||||
clean_release_title = release['title'].translate(str.maketrans('', '', string.punctuation)).lower()
|
||||
clean_artist = artist.translate(str.maketrans('', '', string.punctuation)).lower()
|
||||
|
||||
# prepare search string when title and artist are the same
|
||||
if clean_release_title == clean_artist:
|
||||
# remmove the first acurance of the artist
|
||||
clean_search_string = clean_search_string.replace(clean_artist, "", 1)
|
||||
|
||||
if clean_release_title in clean_search_string:
|
||||
title = release['title']
|
||||
else:
|
||||
print(
|
||||
f"{ULTRASINGER_HEAD} cant find title {red_highlighted(clean_release_title)} in {red_highlighted(clean_search_string)}")
|
||||
|
||||
if title is None or artist is None:
|
||||
print(f"{ULTRASINGER_HEAD} {red_highlighted('No match found')}")
|
||||
return None, None, None, None
|
||||
|
||||
print(f"{ULTRASINGER_HEAD} Found Titel and Artist {blue_highlighted(title)} by {blue_highlighted(artist)}")
|
||||
|
||||
year = None
|
||||
if 'first-release-date' in release:
|
||||
year = release['first-release-date']
|
||||
print(f"{ULTRASINGER_HEAD} Found release year: {blue_highlighted(year)}")
|
||||
|
||||
genres = None
|
||||
if 'tag-list' in release:
|
||||
genres = ""
|
||||
for tag in release['tag-list']:
|
||||
genres += f"{tag['name']},"
|
||||
print(f"{ULTRASINGER_HEAD} Found genres: {blue_highlighted(genres)}")
|
||||
|
||||
return title, artist, year, genres
|
||||
@@ -3,7 +3,7 @@
|
||||
import os
|
||||
import shutil
|
||||
|
||||
from src.modules.console_colors import ULTRASINGER_HEAD
|
||||
from modules.console_colors import ULTRASINGER_HEAD
|
||||
|
||||
|
||||
def create_folder(folder_name: str) -> None:
|
||||
@@ -19,11 +19,16 @@ def move(original: str, target: str) -> None:
|
||||
shutil.move(original, target)
|
||||
|
||||
|
||||
def copy(original:str, target: str) -> None:
|
||||
def copy(original: str, target: str) -> None:
|
||||
"""Copies a file from one location to another."""
|
||||
shutil.copy(original, target)
|
||||
|
||||
|
||||
def rename(original: str, target: str) -> None:
|
||||
"""Renames a file."""
|
||||
os.rename(original, target)
|
||||
|
||||
|
||||
def current_executor_path() -> str:
|
||||
"""Current executor path"""
|
||||
return os.getcwd()
|
||||
|
||||
+3
-3
@@ -4,9 +4,9 @@ import os
|
||||
import librosa
|
||||
from matplotlib import pyplot as plt
|
||||
from matplotlib.patches import Rectangle
|
||||
from src.modules.Pitcher.pitched_data import PitchedData
|
||||
from src.modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
from src.modules.console_colors import ULTRASINGER_HEAD
|
||||
from modules.Pitcher.pitched_data import PitchedData
|
||||
from modules.Speech_Recognition.TranscribedData import TranscribedData
|
||||
from modules.console_colors import ULTRASINGER_HEAD
|
||||
|
||||
|
||||
def get_frequency_range(midi_note: str) -> float:
|
||||
|
||||
Reference in new issue
Block a user