{
"cells": [
{
"cell_type": "code",
"source": [
"#@title # Установка (3 мин без претрейнов)\n",
"%cd /content\n",
"\n",
"from google.colab import files\n",
"import zipfile\n",
"import os\n",
"\n",
"# Загружаем ZIP-файл с устройства\n",
"online = True # @param {\"type\":\"boolean\"}\n",
"if not online:\n",
" uploaded = files.upload()\n",
"else:\n",
" uploaded = \"mvsepless.zip\"\n",
" !wget -O {uploaded} https://huggingface.co/noblebarkrr/mvsepless_updates_zip/resolve/main/mvsepless_alpha_2_ru.zip?download=true\n",
"\n",
"# Проверяем, что файл был загружен\n",
"if not uploaded:\n",
" print(\"Не был загружен ни один файл.\")\n",
"else:\n",
" if not online:\n",
" # Получаем имя загруженного файла (предполагаем, что загружен только один файл)\n",
" zip_filename = next(iter(uploaded))\n",
" else:\n",
" zip_filename = uploaded\n",
" # Путь для распаковки\n",
" extract_to = '/content/mvsepless'\n",
"\n",
" # Создаем папку, если она не существует\n",
" os.makedirs(extract_to, exist_ok=True)\n",
"\n",
" # Распаковываем архив с перезаписью существующих файлов\n",
" with zipfile.ZipFile(zip_filename, 'r') as zip_ref:\n",
" zip_ref.extractall(extract_to)\n",
"\n",
" print(f\"Файл {zip_filename} был успешно распакован в {extract_to} с перезаписью существующих файлов.\")\n",
"\n",
"!cd mvsepless && pip install -r requirements.txt\n",
"!pip install audio-separator[gpu]==0.32.0\n",
"!wget -O mvsepless/models/medley_vox/pretrained_models/xlsr_53_56k.pt https://dl.fbaipublicfiles.com/fairseq/wav2vec/xlsr_53_56k.pt\n",
"!cd mvsepless && python download_models.py"
],
"metadata": {
"cellView": "form",
"id": "9DpDNzJllHCJ",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "615f1b2d-48fb-4675-c94c-9ce0960135fd"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"/content\n",
"--2025-06-03 11:40:42-- https://huggingface.co/noblebarkrr/mvsepless_updates_zip/resolve/main/mvsepless_alpha_2_ru.zip?download=true\n",
"Resolving huggingface.co (huggingface.co)... 13.35.202.34, 13.35.202.40, 13.35.202.121, ...\n",
"Connecting to huggingface.co (huggingface.co)|13.35.202.34|:443... connected.\n",
"HTTP request sent, awaiting response... 302 Found\n",
"Location: https://cdn-lfs-us-1.hf.co/repos/73/59/7359eecc07125fe5d27b22c3fbd8410831156571ee0e8b37bf38b7bff3648cb5/d55570c15c7dc76509d03c201ec0116a5c6135e374eac8b714b332746e0ecd5e?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27mvsepless_alpha_2_ru.zip%3B+filename%3D%22mvsepless_alpha_2_ru.zip%22%3B&response-content-type=application%2Fzip&Expires=1748954442&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTc0ODk1NDQ0Mn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmhmLmNvL3JlcG9zLzczLzU5LzczNTllZWNjMDcxMjVmZTVkMjdiMjJjM2ZiZDg0MTA4MzExNTY1NzFlZTBlOGIzN2JmMzhiN2JmZjM2NDhjYjUvZDU1NTcwYzE1YzdkYzc2NTA5ZDAzYzIwMWVjMDExNmE1YzYxMzVlMzc0ZWFjOGI3MTRiMzMyNzQ2ZTBlY2Q1ZT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoifV19&Signature=Z28T2ki2K34gRyEOcgmxda1uOk-GJZLEMwWDZwOQH25kIEdd4-Vr4V6OlLJ70jQDbwl8jmw0XhcLBwDfO7zkSpOSX6i-P5%7EJYsmMf9WeyG%7EFJgnV%7EscRQWjNS5xUehscr0ukUr3vP7VKchUc-8rdlnFhkeA41lxsC09CmDliFul1k56fbK9t8wjbJCnmoWOMCJW00n9AKV1MK7te6MRhsb2-xOfja08ga08d5LQmZnb58btUxGiEJqMhC2PeHKI0iyjOkF5m%7EIgneH6vVfm4Pn3-v-nC3nRsXFV80TMFQbT-NTR8epkw%7EigGWq2xMT-K2UTIscrJ7Iut2PJZJ4fr-w__&Key-Pair-Id=K24J24Z295AEI9 [following]\n",
"--2025-06-03 11:40:42-- https://cdn-lfs-us-1.hf.co/repos/73/59/7359eecc07125fe5d27b22c3fbd8410831156571ee0e8b37bf38b7bff3648cb5/d55570c15c7dc76509d03c201ec0116a5c6135e374eac8b714b332746e0ecd5e?response-content-disposition=attachment%3B+filename*%3DUTF-8%27%27mvsepless_alpha_2_ru.zip%3B+filename%3D%22mvsepless_alpha_2_ru.zip%22%3B&response-content-type=application%2Fzip&Expires=1748954442&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTc0ODk1NDQ0Mn19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmhmLmNvL3JlcG9zLzczLzU5LzczNTllZWNjMDcxMjVmZTVkMjdiMjJjM2ZiZDg0MTA4MzExNTY1NzFlZTBlOGIzN2JmMzhiN2JmZjM2NDhjYjUvZDU1NTcwYzE1YzdkYzc2NTA5ZDAzYzIwMWVjMDExNmE1YzYxMzVlMzc0ZWFjOGI3MTRiMzMyNzQ2ZTBlY2Q1ZT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoifV19&Signature=Z28T2ki2K34gRyEOcgmxda1uOk-GJZLEMwWDZwOQH25kIEdd4-Vr4V6OlLJ70jQDbwl8jmw0XhcLBwDfO7zkSpOSX6i-P5%7EJYsmMf9WeyG%7EFJgnV%7EscRQWjNS5xUehscr0ukUr3vP7VKchUc-8rdlnFhkeA41lxsC09CmDliFul1k56fbK9t8wjbJCnmoWOMCJW00n9AKV1MK7te6MRhsb2-xOfja08ga08d5LQmZnb58btUxGiEJqMhC2PeHKI0iyjOkF5m%7EIgneH6vVfm4Pn3-v-nC3nRsXFV80TMFQbT-NTR8epkw%7EigGWq2xMT-K2UTIscrJ7Iut2PJZJ4fr-w__&Key-Pair-Id=K24J24Z295AEI9\n",
"Resolving cdn-lfs-us-1.hf.co (cdn-lfs-us-1.hf.co)... 13.33.45.103, 13.33.45.80, 13.33.45.64, ...\n",
"Connecting to cdn-lfs-us-1.hf.co (cdn-lfs-us-1.hf.co)|13.33.45.103|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 24353846 (23M) [application/zip]\n",
"Saving to: ‘mvsepless.zip’\n",
"\n",
"mvsepless.zip 100%[===================>] 23.23M --.-KB/s in 0.1s \n",
"\n",
"2025-06-03 11:40:42 (228 MB/s) - ‘mvsepless.zip’ saved [24353846/24353846]\n",
"\n",
"Файл mvsepless.zip был успешно распакован в /content/mvsepless с перезаписью существующих файлов.\n",
"Processing ./fixed/fairseq_fixed-0.13.0-cp311-cp311-linux_x86_64.whl (from -r requirements.txt (line 36))\n",
"Requirement already satisfied: torch==2.6.0 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 2)) (2.6.0+cu124)\n",
"Requirement already satisfied: torchvision==0.21.0 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 3)) (0.21.0+cu124)\n",
"Requirement already satisfied: torchaudio==2.6.0 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 4)) (2.6.0+cu124)\n",
"Collecting torchcrepe==0.0.23 (from -r requirements.txt (line 5))\n",
" Downloading torchcrepe-0.0.23-py3-none-any.whl.metadata (7.8 kB)\n",
"Requirement already satisfied: numpy==2.0.2 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 6)) (2.0.2)\n",
"Requirement already satisfied: pandas==2.2.2 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 7)) (2.2.2)\n",
"Requirement already satisfied: scipy==1.15.3 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 8)) (1.15.3)\n",
"Collecting librosa==0.9.1 (from -r requirements.txt (line 9))\n",
" Downloading librosa-0.9.1-py3-none-any.whl.metadata (6.9 kB)\n",
"Collecting matplotlib==3.9.0 (from -r requirements.txt (line 10))\n",
" Downloading matplotlib-3.9.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (11 kB)\n",
"Requirement already satisfied: tqdm==4.67.1 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 11)) (4.67.1)\n",
"Requirement already satisfied: einops==0.8.1 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 12)) (0.8.1)\n",
"Requirement already satisfied: protobuf==5.29.4 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 13)) (5.29.4)\n",
"Requirement already satisfied: soundfile==0.13.1 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 16)) (0.13.1)\n",
"Collecting pydub==0.25.1 (from -r requirements.txt (line 17))\n",
" Downloading pydub-0.25.1-py2.py3-none-any.whl.metadata (1.4 kB)\n",
"Collecting pyloudnorm==0.1.1 (from -r requirements.txt (line 18))\n",
" Downloading pyloudnorm-0.1.1-py3-none-any.whl.metadata (5.6 kB)\n",
"Collecting praat-parselmouth==0.4.5 (from -r requirements.txt (line 19))\n",
" Downloading praat_parselmouth-0.4.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.9 kB)\n",
"Collecting webrtcvad==2.0.10 (from -r requirements.txt (line 20))\n",
" Downloading webrtcvad-2.0.10.tar.gz (66 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m66.2/66.2 kB\u001b[0m \u001b[31m6.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting edge-tts==7.0.2 (from -r requirements.txt (line 21))\n",
" Downloading edge_tts-7.0.2-py3-none-any.whl.metadata (5.5 kB)\n",
"Collecting audiomentations==0.24.0 (from -r requirements.txt (line 22))\n",
" Downloading audiomentations-0.24.0-py3-none-any.whl.metadata (35 kB)\n",
"Collecting pedalboard==0.8.1 (from -r requirements.txt (line 23))\n",
" Downloading pedalboard-0.8.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (15 kB)\n",
"Collecting ffmpeg-python==0.2.0 (from -r requirements.txt (line 24))\n",
" Downloading ffmpeg_python-0.2.0-py3-none-any.whl.metadata (1.7 kB)\n",
"Collecting faiss-cpu==1.11 (from -r requirements.txt (line 27))\n",
" Downloading faiss_cpu-1.11.0-cp311-cp311-manylinux_2_28_x86_64.whl.metadata (4.8 kB)\n",
"Collecting ml_collections==1.1.0 (from -r requirements.txt (line 28))\n",
" Downloading ml_collections-1.1.0-py3-none-any.whl.metadata (22 kB)\n",
"Requirement already satisfied: timm==1.0.15 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 29)) (1.0.15)\n",
"Requirement already satisfied: wandb==0.19.11 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 30)) (0.19.11)\n",
"Requirement already satisfied: accelerate==1.7.0 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 31)) (1.7.0)\n",
"Collecting bitsandbytes==0.46.0 (from -r requirements.txt (line 32))\n",
" Downloading bitsandbytes-0.46.0-py3-none-manylinux_2_24_x86_64.whl.metadata (10 kB)\n",
"Collecting tokenizers==0.19 (from -r requirements.txt (line 33))\n",
" Downloading tokenizers-0.19.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n",
"Collecting huggingface-hub==0.28.1 (from -r requirements.txt (line 34))\n",
" Downloading huggingface_hub-0.28.1-py3-none-any.whl.metadata (13 kB)\n",
"Collecting transformers==4.41 (from -r requirements.txt (line 35))\n",
" Downloading transformers-4.41.0-py3-none-any.whl.metadata (43 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.8/43.8 kB\u001b[0m \u001b[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting segmentation_models_pytorch==0.5.0 (from -r requirements.txt (line 39))\n",
" Downloading segmentation_models_pytorch-0.5.0-py3-none-any.whl.metadata (17 kB)\n",
"Collecting torchseg==0.0.1a4 (from -r requirements.txt (line 40))\n",
" Downloading torchseg-0.0.1a4-py3-none-any.whl.metadata (12 kB)\n",
"Collecting demucs==4.0.0 (from -r requirements.txt (line 42))\n",
" Downloading demucs-4.0.0.tar.gz (1.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m65.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting asteroid==0.7.0 (from -r requirements.txt (line 43))\n",
" Downloading asteroid-0.7.0-py3-none-any.whl.metadata (11 kB)\n",
"Collecting prodigyopt==1.1.2 (from -r requirements.txt (line 46))\n",
" Downloading prodigyopt-1.1.2-py3-none-any.whl.metadata (4.8 kB)\n",
"Collecting torch_log_wmse==0.3.0 (from -r requirements.txt (line 47))\n",
" Downloading torch_log_wmse-0.3.0-py3-none-any.whl.metadata (7.4 kB)\n",
"Collecting rotary_embedding_torch==0.6.5 (from -r requirements.txt (line 48))\n",
" Downloading rotary_embedding_torch-0.6.5-py3-none-any.whl.metadata (678 bytes)\n",
"Collecting local-attention==1.11.1 (from -r requirements.txt (line 49))\n",
" Downloading local_attention-1.11.1-py3-none-any.whl.metadata (907 bytes)\n",
"Requirement already satisfied: tenacity==9.1.2 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 52)) (9.1.2)\n",
"Collecting gradio==5.31.0 (from -r requirements.txt (line 53))\n",
" Downloading gradio-5.31.0-py3-none-any.whl.metadata (16 kB)\n",
"Requirement already satisfied: omegaconf==2.3.0 in /usr/local/lib/python3.11/dist-packages (from -r requirements.txt (line 54)) (2.3.0)\n",
"Collecting beartype==0.18.5 (from -r requirements.txt (line 55))\n",
" Downloading beartype-0.18.5-py3-none-any.whl.metadata (30 kB)\n",
"Collecting spafe==0.3.2 (from -r requirements.txt (line 56))\n",
" Downloading spafe-0.3.2-py3-none-any.whl.metadata (8.7 kB)\n",
"Collecting torch_audiomentations==0.12.0 (from -r requirements.txt (line 57))\n",
" Downloading torch_audiomentations-0.12.0-py3-none-any.whl.metadata (15 kB)\n",
"Collecting auraloss==0.4.0 (from -r requirements.txt (line 58))\n",
" Downloading auraloss-0.4.0-py3-none-any.whl.metadata (8.0 kB)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from torch==2.6.0->-r requirements.txt (line 2)) (3.18.0)\n",
"Requirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.11/dist-packages (from torch==2.6.0->-r requirements.txt (line 2)) (4.13.2)\n",
"Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch==2.6.0->-r requirements.txt (line 2)) (3.4.2)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch==2.6.0->-r requirements.txt (line 2)) (3.1.6)\n",
"Requirement already satisfied: fsspec in /usr/local/lib/python3.11/dist-packages (from torch==2.6.0->-r requirements.txt (line 2)) (2025.3.2)\n",
"Collecting nvidia-cuda-nvrtc-cu12==12.4.127 (from torch==2.6.0->-r requirements.txt (line 2))\n",
" Downloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cuda-runtime-cu12==12.4.127 (from torch==2.6.0->-r requirements.txt (line 2))\n",
" Downloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cuda-cupti-cu12==12.4.127 (from torch==2.6.0->-r requirements.txt (line 2))\n",
" Downloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Collecting nvidia-cudnn-cu12==9.1.0.70 (from torch==2.6.0->-r requirements.txt (line 2))\n",
" Downloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Collecting nvidia-cublas-cu12==12.4.5.8 (from torch==2.6.0->-r requirements.txt (line 2))\n",
" Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cufft-cu12==11.2.1.3 (from torch==2.6.0->-r requirements.txt (line 2))\n",
" Downloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-curand-cu12==10.3.5.147 (from torch==2.6.0->-r requirements.txt (line 2))\n",
" Downloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cusolver-cu12==11.6.1.9 (from torch==2.6.0->-r requirements.txt (line 2))\n",
" Downloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Collecting nvidia-cusparse-cu12==12.3.1.170 (from torch==2.6.0->-r requirements.txt (line 2))\n",
" Downloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Requirement already satisfied: nvidia-cusparselt-cu12==0.6.2 in /usr/local/lib/python3.11/dist-packages (from torch==2.6.0->-r requirements.txt (line 2)) (0.6.2)\n",
"Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch==2.6.0->-r requirements.txt (line 2)) (2.21.5)\n",
"Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch==2.6.0->-r requirements.txt (line 2)) (12.4.127)\n",
"Collecting nvidia-nvjitlink-cu12==12.4.127 (from torch==2.6.0->-r requirements.txt (line 2))\n",
" Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Requirement already satisfied: triton==3.2.0 in /usr/local/lib/python3.11/dist-packages (from torch==2.6.0->-r requirements.txt (line 2)) (3.2.0)\n",
"Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch==2.6.0->-r requirements.txt (line 2)) (1.13.1)\n",
"Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/local/lib/python3.11/dist-packages (from torchvision==0.21.0->-r requirements.txt (line 3)) (11.2.1)\n",
"Collecting resampy (from torchcrepe==0.0.23->-r requirements.txt (line 5))\n",
" Downloading resampy-0.4.3-py3-none-any.whl.metadata (3.0 kB)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas==2.2.2->-r requirements.txt (line 7)) (2.9.0.post0)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas==2.2.2->-r requirements.txt (line 7)) (2025.2)\n",
"Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas==2.2.2->-r requirements.txt (line 7)) (2025.2)\n",
"Requirement already satisfied: audioread>=2.1.5 in /usr/local/lib/python3.11/dist-packages (from librosa==0.9.1->-r requirements.txt (line 9)) (3.0.1)\n",
"Requirement already satisfied: scikit-learn>=0.19.1 in /usr/local/lib/python3.11/dist-packages (from librosa==0.9.1->-r requirements.txt (line 9)) (1.6.1)\n",
"Requirement already satisfied: joblib>=0.14 in /usr/local/lib/python3.11/dist-packages (from librosa==0.9.1->-r requirements.txt (line 9)) (1.5.0)\n",
"Requirement already satisfied: decorator>=4.0.10 in /usr/local/lib/python3.11/dist-packages (from librosa==0.9.1->-r requirements.txt (line 9)) (4.4.2)\n",
"Requirement already satisfied: numba>=0.45.1 in /usr/local/lib/python3.11/dist-packages (from librosa==0.9.1->-r requirements.txt (line 9)) (0.60.0)\n",
"Requirement already satisfied: pooch>=1.0 in /usr/local/lib/python3.11/dist-packages (from librosa==0.9.1->-r requirements.txt (line 9)) (1.8.2)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from librosa==0.9.1->-r requirements.txt (line 9)) (24.2)\n",
"Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib==3.9.0->-r requirements.txt (line 10)) (1.3.2)\n",
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.11/dist-packages (from matplotlib==3.9.0->-r requirements.txt (line 10)) (0.12.1)\n",
"Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib==3.9.0->-r requirements.txt (line 10)) (4.58.0)\n",
"Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib==3.9.0->-r requirements.txt (line 10)) (1.4.8)\n",
"Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib==3.9.0->-r requirements.txt (line 10)) (3.2.3)\n",
"Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.11/dist-packages (from soundfile==0.13.1->-r requirements.txt (line 16)) (1.17.1)\n",
"Requirement already satisfied: future>=0.16.0 in /usr/local/lib/python3.11/dist-packages (from pyloudnorm==0.1.1->-r requirements.txt (line 18)) (1.0.0)\n",
"Requirement already satisfied: aiohttp<4.0.0,>=3.8.0 in /usr/local/lib/python3.11/dist-packages (from edge-tts==7.0.2->-r requirements.txt (line 21)) (3.11.15)\n",
"Requirement already satisfied: certifi>=2023.11.17 in /usr/local/lib/python3.11/dist-packages (from edge-tts==7.0.2->-r requirements.txt (line 21)) (2025.4.26)\n",
"Collecting srt<4.0.0,>=3.4.1 (from edge-tts==7.0.2->-r requirements.txt (line 21))\n",
" Downloading srt-3.5.3.tar.gz (28 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: tabulate<1.0.0,>=0.4.4 in /usr/local/lib/python3.11/dist-packages (from edge-tts==7.0.2->-r requirements.txt (line 21)) (0.9.0)\n",
"Requirement already satisfied: absl-py in /usr/local/lib/python3.11/dist-packages (from ml_collections==1.1.0->-r requirements.txt (line 28)) (1.4.0)\n",
"Requirement already satisfied: PyYAML in /usr/local/lib/python3.11/dist-packages (from ml_collections==1.1.0->-r requirements.txt (line 28)) (6.0.2)\n",
"Requirement already satisfied: safetensors in /usr/local/lib/python3.11/dist-packages (from timm==1.0.15->-r requirements.txt (line 29)) (0.5.3)\n",
"Requirement already satisfied: click!=8.0.0,>=7.1 in /usr/local/lib/python3.11/dist-packages (from wandb==0.19.11->-r requirements.txt (line 30)) (8.2.1)\n",
"Requirement already satisfied: docker-pycreds>=0.4.0 in /usr/local/lib/python3.11/dist-packages (from wandb==0.19.11->-r requirements.txt (line 30)) (0.4.0)\n",
"Requirement already satisfied: gitpython!=3.1.29,>=1.0.0 in /usr/local/lib/python3.11/dist-packages (from wandb==0.19.11->-r requirements.txt (line 30)) (3.1.44)\n",
"Requirement already satisfied: platformdirs in /usr/local/lib/python3.11/dist-packages (from wandb==0.19.11->-r requirements.txt (line 30)) (4.3.8)\n",
"Requirement already satisfied: psutil>=5.0.0 in /usr/local/lib/python3.11/dist-packages (from wandb==0.19.11->-r requirements.txt (line 30)) (5.9.5)\n",
"Requirement already satisfied: pydantic<3 in /usr/local/lib/python3.11/dist-packages (from wandb==0.19.11->-r requirements.txt (line 30)) (2.11.4)\n",
"Requirement already satisfied: requests<3,>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from wandb==0.19.11->-r requirements.txt (line 30)) (2.32.3)\n",
"Requirement already satisfied: sentry-sdk>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from wandb==0.19.11->-r requirements.txt (line 30)) (2.29.1)\n",
"Requirement already satisfied: setproctitle in /usr/local/lib/python3.11/dist-packages (from wandb==0.19.11->-r requirements.txt (line 30)) (1.3.6)\n",
"Requirement already satisfied: setuptools in /usr/local/lib/python3.11/dist-packages (from wandb==0.19.11->-r requirements.txt (line 30)) (75.2.0)\n",
"Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.11/dist-packages (from transformers==4.41->-r requirements.txt (line 35)) (2024.11.6)\n",
"Collecting dora-search (from demucs==4.0.0->-r requirements.txt (line 42))\n",
" Downloading dora_search-0.1.12.tar.gz (87 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m87.1/87.1 kB\u001b[0m \u001b[31m8.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "HyxHY762qmyE"
},
"source": [
"# NON-CLI"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "18XSjQzyyl5E"
},
"outputs": [],
"source": [
"# @title Mvsepless & Vbach (напрямую в ячейке)\n",
"#@markdown Разделение / замена музыки и голоса\n",
"\n",
"%cd /content/mvsepless\n",
"\n",
"import gradio as gr\n",
"from multi_infer import theme, mvsepless_non_cli\n",
"\n",
"with gr.Blocks(title=\"Разделение музыки и голоса\", theme=theme) as demo:\n",
" gr.HTML(\" MVSEPLESS
\")\n",
" mvsepless_non_cli(True)\n",
" demo.launch(share=True, allowed_paths=[\"/content\"])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "JMZh5sYvoeuq"
},
"outputs": [],
"source": [
"# @title VbachGen\n",
"#@markdown Быстрая генерация сурсов для ИИ-каверов\n",
"%cd /content/mvsepless\n",
"!python gencover.py"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "VNW0Op_Nsbql"
},
"outputs": [],
"source": [
"# @title Mvsepless\n",
"#@markdown Разделение музыки и голоса\n",
"\n",
"%cd /content/mvsepless\n",
"!python multi_infer.py -gr"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "TmxdFPBXXC-c"
},
"outputs": [],
"source": [
"# @title Mvsepless & Vbach\n",
"#@markdown Разделение / Замена музыки и голоса\n",
"\n",
"%cd /content/mvsepless\n",
"!python multi_infer.py -grvc"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "n3PP3N-spH_0"
},
"source": [
"# CLI"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "sOrwMYdj_cuF"
},
"outputs": [],
"source": [
"# @title Объединить аудио файлы в ансамбль\n",
"\n",
"import os\n",
"import numpy\n",
"\n",
"%cd /content/mvsepless\n",
"\n",
"from ensem import ensemble_audio_files\n",
"from infer_utils.audio_processing.invert import invert_and_overlay_wav\n",
"\n",
"\n",
"input = \"\" # @param {\"type\":\"string\",\"placeholder\":\"Введите путь к папке с результатами моделей\"}\n",
"input_orig = \"\" # @param {\"type\":\"string\",\"placeholder\":\"Введите путь к оригинальному аудио\"}\n",
"output = \"\" # @param {\"type\":\"string\",\"placeholder\":\"Введите путь к папке сохранения результатов\"}\n",
"\n",
"type = \"max_fft\" # @param [\"max_fft\",\"min_fft\",\"median_fft\",\"max_wave\",\"avg_fft\"]\n",
"\n",
"# Создаем выходную директорию, если ее нет\n",
"os.makedirs(output, exist_ok=True)\n",
"\n",
"# Проверяем существование входной директории\n",
"if not os.path.exists(input):\n",
" raise FileNotFoundError(f\"Input directory {input} does not exist\")\n",
"\n",
"# Получаем список файлов\n",
"temp_ensem_files = [os.path.abspath(os.path.join(input, f))\n",
" for f in os.listdir(input)\n",
" if os.path.isfile(os.path.join(input, f))]\n",
"\n",
"if not temp_ensem_files:\n",
" raise ValueError(\"No files found in input directory\")\n",
"\n",
"weight_value = 1.0 # @param {\"type\":\"number\"}\n",
"weights = [weight_value] * len(temp_ensem_files)\n",
"\n",
"output_file = os.path.join(output, \"output.wav\")\n",
"inverted_file = os.path.join(output, \"inverted.wav\")\n",
"\n",
"ensemble_audio_files(files=temp_ensem_files, output=output_file, ensemble_type=type, weights=weights)\n",
"if input_orig != \"\":\n",
" invert_and_overlay_wav(output_file, input_orig, inverted_file)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "P3tLD2QXqyqp"
},
"source": [
"## Разделить аудио"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "QmK2R6skpvR8"
},
"outputs": [],
"source": [
"# @title Получить список моделей\n",
"\n",
"%cd /content/mvsepless\n",
"\n",
"model_type = \"mel_band_roformer\" # @param [\"mel_band_roformer\",\"bs_roformer\",\"mdx23c\",\"vr_arch\",\"htdemucs\",\"scnet\",\"mdx_net\",\"medley_vox\",\"bandit\",\"bandit_v2\"]\n",
"\n",
"from model_info import model_info\n",
"model_info(model_type)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "V8MI-asTQAz4"
},
"outputs": [],
"source": [
"# @title Инференс\n",
"\n",
"%cd /content/mvsepless\n",
"\n",
"#@markdown Чтобы получить информацию о моделях, запустите ячейку 'Получить список моделей' с нужным типом модели\n",
"\n",
"template = \"NAME_MODEL_STEM\" # @param {\"type\":\"string\",\"placeholder\":\"Шаблон имени стемов, пример: NAME_MODEL_STEM\"}\n",
"\n",
"model_type = \"mel_band_roformer\" # @param [\"mel_band_roformer\",\"bs_roformer\",\"mdx23c\",\"vr_arch\",\"htdemucs\",\"scnet\",\"mdx_net\",\"medley_vox\",\"bandit\",\"bandit_v2\"]\n",
"model_name = \"\" # @param {\"type\":\"string\",\"placeholder\":\"Введите имя модели, которое есть в списке моделей (Можно получить список используя ячейку выше)\"}\n",
"input = \"\" # @param {\"type\":\"string\",\"placeholder\":\"Введите путь к аудиофайлу/папке с аудиофайлами\"}\n",
"output = \"\" # @param {\"type\":\"string\",\"placeholder\":\"Введите путь к папке сохранения стемов\"}\n",
"\n",
"output_format = \"flac\" # @param [\"wav\",\"mp3\",\"flac\",\"m4a\",\"aac\",\"opus\"]\n",
"batch = False # @param {\"type\":\"boolean\"}\n",
"tta = False\n",
"select_stems = \"\" # @param {\"type\":\"string\",\"placeholder\":\"Введите стемы, которые хотите сохранить, пример: 'vocals drums' или 'male female karaoke''\"}\n",
"\n",
"# @markdown \n",
"# @markdown Описание настроек
\n",
"# @markdown\n",
"# @markdown > * template - Формат имени результатов разделения.\n",
"# @markdown >\n",
"# @markdown > Существуют три ключа:\n",
"# @markdown >\n",
"# @markdown > > NAME - название оригинального аудио файла (без расширения)\n",
"# @markdown >\n",
"# @markdown > > MODEL - название модели, использованной для разделения на стемы\n",
"# @markdown >\n",
"# @markdown > > STEM - название стема\n",
"# @markdown >\n",
"# @markdown > > DATETIME - дата и время создвния файла\n",
"# @markdown >\n",
"# @markdown > Пример:\n",
"# @markdown >\n",
"# @markdown > NAME_STEM --> вход_vocals.mp3\n",
"# @markdown >\n",
"# @markdown > > NAME - 'вход'\n",
"# @markdown >\n",
"# @markdown > > STEM - vocals\n",
"# @markdown >\n",
"# @markdown > MODEL_STEM --> mel_band_roformer_aname_4_stems_large_drums.mp3\n",
"# @markdown >\n",
"# @markdown > > MODEL - 'mel_band_roformer_aname_4_stems_large'\n",
"# @markdown >\n",
"# @markdown > > STEM - drums\n",
"# @markdown >\n",
"# @markdown > mvsepless_STEM --> mvsepless_karaoke.mp3\n",
"# @markdown >\n",
"# @markdown > > mvsepless - mvsepless (кастомное имя)\n",
"# @markdown >\n",
"# @markdown > > STEM - karaoke\n",
"# @markdown >\n",
"# @markdown\n",
"# @markdown > * batch - Пакетная обработка. Включается при batch = True\n",
"# @markdown >\n",
"# @markdown > (В нашем случае если поставлена галочка напротив batch)\n",
"# @markdown >\n",
"# @markdown > Включено - обрабатывается папка с аудиофайлами\n",
"# @markdown >\n",
"# @markdown > Выключено - обрабатывается один аудиофайл\n",
"# @markdown\n",
"# @markdown > * select_stems - Выбор стемов для разделения\n",
"# @markdown >\n",
"# @markdown > Не работает с:\n",
"# @markdown >\n",
"# @markdown > > моделями на архитектуре Medley-Vox\n",
"# @markdown >\n",
"# @markdown > > моделями с целевым инструментом (Target Instrument is not \"No\")\n",
"# @markdown >\n",
"# @markdown > > моделями на архитектуре MDX-NET и VR ARCH, если выбрано больше одного стема\n",
"# @markdown\n",
"# @markdown > * model_type - Тип модели, то есть её архитектура\n",
"# @markdown\n",
"# @markdown > * model_name - Название модели для разделения вокала\n",
"\n",
"run_command = f'python multi_infer.py -i \"{input}\" -o {output} -of {output_format} {(\"--use_tta\" if tta else \"\")} {(\"--batch\" if batch else \"\")} -inst --model_type {model_type} --model_name {model_name} {(f\"--select {select_stems}\" if select_stems != \"\" else \"\")} --template {template}'\n",
"!$run_command"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "PTzLZWnWq3c8"
},
"source": [
"## Замена вокала"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "TVQeDhtMPwgU"
},
"outputs": [],
"source": [
"\n",
"%cd /content/mvsepless\n",
"\n",
"import os\n",
"from datetime import datetime\n",
"from rvc.scripts.voice_conversion import voice_pipeline\n",
"\n",
"\n",
"def voice_conversion(input, model, pitch, ir, fr, rms, f0, hop, prtct, of, f0_min, f0_max, output, template, batch):\n",
" if batch:\n",
" for filename in os.listdir(input):\n",
" file = os.path.join(input, filename)\n",
" if os.path.isfile(file):\n",
" file_name = os.path.basename(file)\n",
" namefile = os.path.splitext(file_name)[0]\n",
" time_create_file = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
" output_name = (\n",
" template\n",
" .replace(\"DATETIME\", time_create_file)\n",
" .replace(\"NAME\", namefile)\n",
" .replace(\"MODEL\", model)\n",
" .replace(\"F0METHOD\", f0)\n",
" .replace(\"PITCH\", f\"{pitch}\")\n",
" )\n",
" voice_pipeline(file, model, pitch, ir, fr, rms, f0, hop, prtct, of, f0_min, f0_max, output, output_name)\n",
" else:\n",
" time_create_file = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
" output_name = (\n",
" template\n",
" .replace(\"DATETIME\", time_create_file)\n",
" .replace(\"NAME\", namefile)\n",
" .replace(\"MODEL\", model)\n",
" .replace(\"F0METHOD\", f0)\n",
" .replace(\"PITCH\", pitch)\n",
" )\n",
" voice_pipeline(input, model, pitch, ir, fr, rms, f0, hop, prtct, of, f0_min, f0_max, output, output_name)\n",
"\n",
"\n",
"song_input = \"\" # @param {type:\"string\"}\n",
"model_name = \"\" # @param {type:\"string\"}\n",
"batch = False # @param {\"type\":\"boolean\"}\n",
"\n",
"# @markdown #### Основные настройки\n",
"pitch = 0 # @param {type:\"slider\", min:-48, max:48, step:12}\n",
"index_rate = 0 # @param {type:\"slider\", min:0, max:1, step:0.01}\n",
"filter_radius = 3 # @param {type:\"slider\", min:0, max:7, step:1}\n",
"volume_envelope = 0.25 # @param {type:\"slider\", min:0, max:1, step:0.01}\n",
"\n",
"# @markdown #### Настройки F0\n",
"method = \"rmvpe+\" # @param [\"rmvpe+\", \"mangio-crepe\", \"fcpe\"]\n",
"hop_length = 128 # @param {type:\"slider\", min:32, max:512, step:16}\n",
"protect = 0.33 # @param {type:\"slider\", min:0, max:0.5, step:0.01}\n",
"f0_min = 50 # @param {type:\"slider\", min:0, max:500, step:1}\n",
"f0_max = 1100 # @param {type:\"slider\", min:100, max:2000, step:10}\n",
"\n",
"# @markdown #### Выходные настройки\n",
"output_format = \"mp3\" # @param [\"mp3\", \"wav\", \"flac\"]\n",
"output_path = \"\" # @param {type:\"string\"}\n",
"\n",
"# Задаем шаблон вручную (можно менять порядок и состав)\n",
"template = \"DATETIME_NAME_PITCH\" # @param {type:\"string\"}\n",
"\n",
"voice_conversion(song_input, model_name, pitch, index_rate, filter_radius, volume_envelope, method, hop_length, protect, output_format, f0_min, f0_max, output_path, template, batch)"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"collapsed_sections": [
"n3PP3N-spH_0",
"P3tLD2QXqyqp",
"PTzLZWnWq3c8"
],
"gpuType": "T4",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}