File size: 13,165 Bytes
3b7b011 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 |
import sys
sys.path.append("..")
import os
import shutil
now_dir = os.getcwd()
import soundfile as sf
import librosa
from lib.tools import audioEffects
from assets.i18n.i18n import I18nAuto
i18n = I18nAuto()
import gradio as gr
import tabs.resources as resources
import numpy as np
from scipy.signal import resample
def save_to_wav2(dropbox):
file_path = dropbox.name
target_path = os.path.join("assets","audios", os.path.basename(file_path))
if os.path.exists(target_path):
os.remove(target_path)
print("Replacing old dropdown file...")
shutil.move(file_path, target_path)
return target_path
audio_root = "assets/audios"
audio_others_root = "assets/audios/audio-others"
sup_audioext = {
"wav",
"mp3",
"flac",
"ogg",
"opus",
"m4a",
"mp4",
"aac",
"alac",
"wma",
"aiff",
"webm",
"ac3",
}
audio_paths = [
os.path.join(root, name)
for root, _, files in os.walk(audio_root, topdown=False)
for name in files
if name.endswith(tuple(sup_audioext)) and root == audio_root
]
audio_others_paths = [
os.path.join(root, name)
for root, _, files in os.walk(audio_others_root, topdown=False)
for name in files
if name.endswith(tuple(sup_audioext)) and root == audio_others_root
]
def change_choices3():
audio_paths = [
os.path.join(root, name)
for root, _, files in os.walk(audio_root, topdown=False)
for name in files
if name.endswith(tuple(sup_audioext)) and root == audio_root
]
audio_others_paths = [
os.path.join(root, name)
for root, _, files in os.walk(audio_others_root, topdown=False)
for name in files
if name.endswith(tuple(sup_audioext)) and root == audio_others_root
]
return (
{"choices": sorted(audio_others_paths), "__type__": "update"},
{"choices": sorted(audio_paths), "__type__": "update"},
)
def generate_output_path(output_folder, base_name, extension):
index = 1
while True:
output_path = os.path.join(output_folder, f"{base_name}_{index}.{extension}")
if not os.path.exists(output_path):
return output_path
index += 1
from pydub import AudioSegment
from pydub.silence import detect_nonsilent
import glob
import re
def combine_and_save_audios(
audio1_path, audio2_path, output_path, volume_factor_audio1, volume_factor_audio2
):
audio1 = AudioSegment.from_file(audio1_path)
audio2 = AudioSegment.from_file(audio2_path)
# Verificar cu谩l audio tiene mayor longitud
if len(audio1) > len(audio2):
# Calcular la diferencia en duraci贸n en segundos
diff_duration_seconds = (len(audio1) - len(audio2)) / 1000.0 # Convertir a segundos
print(f"diff_duration_seconds: {diff_duration_seconds} seconds")
# Crear el segmento de silencio en Pydub
silence = AudioSegment.silent(duration=int(diff_duration_seconds)) # Convertir a milisegundos
# Agregar el silencio al audio2 para igualar la duraci贸n
audio2 = audio2 + silence
else:
# Calcular la diferencia en duraci贸n en segundos
diff_duration_seconds = (len(audio2) - len(audio1)) / 1000.0 # Convertir a segundos
print(f"diff_duration_seconds: {diff_duration_seconds} seconds")
# Crear el segmento de silencio en Pydub
silence = AudioSegment.silent(duration=int(diff_duration_seconds)) # Convertir a milisegundos
# Agregar el silencio al audio1 para igualar la duraci贸n
audio1 = audio1 + silence
# Ajustar el volumen de los audios multiplicando por el factor de ganancia
if volume_factor_audio1 != 1.0:
audio1 *= volume_factor_audio1
if volume_factor_audio2 != 1.0:
audio2 *= volume_factor_audio2
# Combinar los audios
combined_audio = audio1.overlay(audio2)
# Guardar el audio combinado en el archivo de salida
combined_audio.export(output_path, format="wav")
def audio_combined(
audio1_path,
audio2_path,
volume_factor_audio1=1.0,
volume_factor_audio2=1.0,
reverb_enabled=False,
compressor_enabled=False,
noise_gate_enabled=False,
):
output_folder = os.path.join(now_dir,"assets", "audios", "audio-outputs")
os.makedirs(output_folder, exist_ok=True)
# Generar nombres 煤nicos para los archivos de salida
base_name = "combined_audio"
extension = "wav"
output_path = generate_output_path(output_folder, base_name, extension)
print(reverb_enabled)
print(compressor_enabled)
print(noise_gate_enabled)
if reverb_enabled or compressor_enabled or noise_gate_enabled:
# Procesa el primer audio con los efectos habilitados
base_name = "effect_audio"
output_path = generate_output_path(output_folder, base_name, extension)
processed_audio_path = audioEffects.process_audio(
audio2_path,
output_path,
reverb_enabled,
compressor_enabled,
noise_gate_enabled,
)
base_name = "combined_audio"
output_path = generate_output_path(output_folder, base_name, extension)
# Combina el audio procesado con el segundo audio usando audio_combined
combine_and_save_audios(
audio1_path,
processed_audio_path,
output_path,
volume_factor_audio1,
volume_factor_audio2,
)
return i18n("Conversion complete!"), output_path
else:
base_name = "combined_audio"
output_path = generate_output_path(output_folder, base_name, extension)
# No hay efectos habilitados, combina directamente los audios sin procesar
combine_and_save_audios(
audio1_path,
audio2_path,
output_path,
volume_factor_audio1,
volume_factor_audio2,
)
return i18n("Conversion complete!"), output_path
def process_audio(file_path):
try:
# load audio file
song = AudioSegment.from_file(file_path)
print(f"Ignore the warning if you saw any...")
# set silence threshold and duration
silence_thresh = -70 # dB
min_silence_len = 750 # ms, adjust as needed
# detect nonsilent parts
nonsilent_parts = detect_nonsilent(song, min_silence_len=min_silence_len, silence_thresh=silence_thresh)
# Create a new directory to store chunks
file_dir = os.path.dirname(file_path)
file_name = os.path.basename(file_path).split('.')[0]
new_dir_path = os.path.join(file_dir, file_name)
os.makedirs(new_dir_path, exist_ok=True)
# Check if timestamps file exists, if so delete it
timestamps_file = os.path.join(file_dir, f"{file_name}_timestamps.txt")
if os.path.isfile(timestamps_file):
os.remove(timestamps_file)
# export chunks and save start times
segment_count = 0
for i, (start_i, end_i) in enumerate(nonsilent_parts):
chunk = song[start_i:end_i]
chunk_file_path = os.path.join(new_dir_path, f"chunk{i}.wav")
chunk.export(chunk_file_path, format="wav")
print(f"Segment {i} created!")
segment_count += 1
# write start times to file
with open(timestamps_file, "a", encoding="utf-8") as f:
f.write(f"{chunk_file_path} starts at {start_i} ms\n")
print(f"Total segments created: {segment_count}")
print(f"Split all chunks for {file_path} successfully!")
return "Finish", new_dir_path
except Exception as e:
print(f"An error occurred: {e}")
return "Error", None
def merge_audio(timestamps_file):
try:
# Extract prefix from the timestamps filename
prefix = os.path.basename(timestamps_file).replace('_timestamps.txt', '')
timestamps_dir = os.path.dirname(timestamps_file)
print(timestamps_dir)
print(prefix)
# Open the timestamps file
with open(timestamps_file, "r", encoding="utf-8") as f:
lines = f.readlines()
# Initialize empty list to hold audio segments
audio_segments = []
last_end_time = 0
print(f"Processing file: {timestamps_file}")
for line in lines:
# Extract filename and start time from line
match = re.search(r"(chunk\d+.wav) starts at (\d+) ms", line)
if match:
filename, start_time = match.groups()
start_time = int(start_time)
# Construct the complete path to the chunk file
chunk_file = os.path.join(timestamps_dir, prefix, filename)
# Add silence from last_end_time to start_time
silence_duration = max(start_time - last_end_time, 0)
silence = AudioSegment.silent(duration=silence_duration)
audio_segments.append(silence)
# Load audio file and append to list
audio = AudioSegment.from_wav(chunk_file)
audio_segments.append(audio)
# Update last_end_time
last_end_time = start_time + len(audio)
print(f"Processed chunk: {chunk_file}")
# Concatenate all audio_segments and export
merged_filename = f"{prefix}_merged.wav"
merged_audio = sum(audio_segments)
merged_audio.export(os.path.join(timestamps_dir, "audio-outputs", merged_filename), format="wav")
print(f"Exported merged file: {merged_filename}\n")
except Exception as e:
print(f"An error occurred: {e}")
def merge_audios():
gr.Markdown(
value="## " + i18n("Merge your generated audios with the instrumental")
)
with gr.Row():
with gr.Column():
dropbox = gr.File(label=i18n("Drag your audio here:"))
gr.Markdown(value=i18n("### Instrumental settings:"))
input_audio1 = gr.Dropdown(
label=i18n("Choose your instrumental:"),
choices=sorted(audio_others_paths),
value="",
interactive=True,
)
input_audio1_scale = gr.Slider(
minimum=0,
maximum=10,
label=i18n("Volume of the instrumental audio:"),
value=1.00,
interactive=True,
)
gr.Markdown(value=i18n("### Audio settings:"))
input_audio3 = gr.Dropdown(
label=i18n("Select the generated audio"),
choices=sorted(audio_paths),
value="",
interactive=True,
)
with gr.Row():
input_audio3_scale = gr.Slider(
minimum=0,
maximum=10,
label=i18n("Volume of the generated audio:"),
value=1.00,
interactive=True,
)
gr.Markdown(value=i18n("### Add the effects:"))
reverb_ = gr.Checkbox(
label=i18n("Reverb"),
value=False,
interactive=True,
)
compressor_ = gr.Checkbox(
label=i18n("Compressor"),
value=False,
interactive=True,
)
noise_gate_ = gr.Checkbox(
label=i18n("Noise Gate"),
value=False,
interactive=True,
)
with gr.Row():
butnone = gr.Button(i18n("Merge"), variant="primary").style(
full_width=True
)
refresh_button = gr.Button(
i18n("Refresh"), variant="primary"
).style(full_width=True)
vc_output1 = gr.Textbox(label=i18n("Output information:"))
vc_output2 = gr.Audio(
label=i18n(
"Export audio (click on the three dots in the lower right corner to download)"
),
type="filepath",
)
dropbox.upload(
fn=save_to_wav2, inputs=[dropbox], outputs=[input_audio1]
)
refresh_button.click(
fn=lambda: change_choices3(),
inputs=[],
outputs=[input_audio1, input_audio3],
)
butnone.click(
fn=audio_combined,
inputs=[
input_audio1,
input_audio3,
input_audio1_scale,
input_audio3_scale,
reverb_,
compressor_,
noise_gate_,
],
outputs=[vc_output1, vc_output2],
)
|