pymss 1.0__tar.gz

pymss-1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 KitsuneX07
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

pymss-1.0/PKG-INFO

@@ -0,0 +1,128 @@
+Metadata-Version: 2.1
+Name: pymss
+Version: 1.0
+Summary: Python package for music source separation.
+Home-page: https://github.com/KitsuneX07/pymss
+Author: KitsuneX07
+Author-email: ghast1085654218@163.com
+License: MIT
+Project-URL: Bug Tracker, https://github.com/KitsuneX07/pymss/issues
+Project-URL: Source Code, https://github.com/KitsuneX07/pymss
+Project-URL: Documentation, https://github.com/KitsuneX07/pymss/blob/main/README.md
+Keywords: music source separation,audio separation,music processing,machine learning,audio
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Multimedia :: Sound/Audio
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydub
+Requires-Dist: numpy
+Requires-Dist: torch
+Requires-Dist: torchaudio
+Requires-Dist: librosa
+Requires-Dist: soundfile
+Requires-Dist: tqdm
+Requires-Dist: ml-collections
+Requires-Dist: omegaconf
+Requires-Dist: pyyaml
+Requires-Dist: demucs
+Requires-Dist: colorama
+Requires-Dist: pytorch_lightning
+Requires-Dist: asteroid
+Requires-Dist: spafe
+Requires-Dist: pedalboard
+Requires-Dist: torch_audiomentations
+Requires-Dist: beartype
+Requires-Dist: rotary_embedding_torch
+Requires-Dist: transformers
+Requires-Dist: segmentation_models_pytorch
+
+# pymss
+
+Python package for music source separation.
+
+
+## Install
+
+Example of using pip to install `pymss` package：
+
+```sh
+pip install pymss
+```
+
+## Usage
+
+Here's a simple example.
+```python
+from pymss MSSeparator, get_separation_logger
+
+# init
+separator = MSSeparator(
+    model_type='htdemucs', 
+    model_path='path/to/model',
+    config_path='path/to/config',
+    device='cuda',
+    device_ids=[0],
+    output_format='wav',
+    use_tta=True,
+    store_dirs={
+        "vocals": "./output/vocals",
+        "other": None # None or missing this stem will result in no output file for this stem. This example will output the vocal's stem in ./output/vocals and ignoring the other(instrumental) stem. Making sure the key(s) match the config file.
+    },
+    audio_params={"wav_bit_depth": "FLOAT", "flac_bit_depth": "PCM_24", "mp3_bit_rate": "320k"}, # Can be omitted
+    logger=get_separation_logger(), # Can be omitted
+    debug=False, # Can be omitted
+    inference_params={
+        "batch_size": 4,
+        "num_overlap": 1,
+        "chunk_size": 1024,
+        "normalize": True
+    } # Can be omitted
+)
+
+# process all audio files in the folder
+separator.process_folder('path/to/input_folder')
+```
+
+### Parameters
+
+- model_type: The type of model, e.g., 'htdemucs'. Must be one of 
+    ['bs_roformer', 
+    'mel_band_roformer', 
+    'segm_models', 
+    'htdemucs', 
+    'mdx23c', 
+    'swin_upernet', 
+    'bandit', 
+    'bandit_v2', 
+    'scnet', 
+    'scnet_unofficial', 
+    'torchseg', 
+    'apollo', 
+    'bs_mamba2']
+- model_path: The path to the model file.
+- config_path: The path to the configuration file.
+- device: The type of device, default is 'auto'. Must be one of ['auto', 'cuda', 'mps', 'cpu']
+- device_ids: List of device IDs, default is [0].
+- output_format: The output audio format, default is 'wav'. Must be one of ['wav', 'flac', 'mp3']
+- use_tta: Whether to use TTA, default is False. Using TTA will triple the processing time with a little bit improvement in quality.
+- store_dirs: Storage directories, can be a single folder path or a dictionary with instrument keys.
+- audio_params: Audio parameters including wav_bit_depth, flac_bit_depth, and mp3_bit_rate. Default is {"wav_bit_depth": "FLOAT", "flac_bit_depth": "PCM_24", "mp3_bit_rate": "320k"}.
+- logger: Logger instance. Default is pymss.get_separation_logger()
+- debug: Whether to enable debug mode, default is False.
+- inference_params: Inference parameters including batch_size, num_overlap, chunk_size, and normalize. Default is all None (means all params are depended on the config file).
+
+## Contributing
+Contributions are welcome! 

pymss-1.0/README.md

@@ -0,0 +1,77 @@
+# pymss
+
+Python package for music source separation.
+
+
+## Install
+
+Example of using pip to install `pymss` package：
+
+```sh
+pip install pymss
+```
+
+## Usage
+
+Here's a simple example.
+```python
+from pymss MSSeparator, get_separation_logger
+
+# init
+separator = MSSeparator(
+    model_type='htdemucs', 
+    model_path='path/to/model',
+    config_path='path/to/config',
+    device='cuda',
+    device_ids=[0],
+    output_format='wav',
+    use_tta=True,
+    store_dirs={
+        "vocals": "./output/vocals",
+        "other": None # None or missing this stem will result in no output file for this stem. This example will output the vocal's stem in ./output/vocals and ignoring the other(instrumental) stem. Making sure the key(s) match the config file.
+    },
+    audio_params={"wav_bit_depth": "FLOAT", "flac_bit_depth": "PCM_24", "mp3_bit_rate": "320k"}, # Can be omitted
+    logger=get_separation_logger(), # Can be omitted
+    debug=False, # Can be omitted
+    inference_params={
+        "batch_size": 4,
+        "num_overlap": 1,
+        "chunk_size": 1024,
+        "normalize": True
+    } # Can be omitted
+)
+
+# process all audio files in the folder
+separator.process_folder('path/to/input_folder')
+```
+
+### Parameters
+
+- model_type: The type of model, e.g., 'htdemucs'. Must be one of 
+    ['bs_roformer', 
+    'mel_band_roformer', 
+    'segm_models', 
+    'htdemucs', 
+    'mdx23c', 
+    'swin_upernet', 
+    'bandit', 
+    'bandit_v2', 
+    'scnet', 
+    'scnet_unofficial', 
+    'torchseg', 
+    'apollo', 
+    'bs_mamba2']
+- model_path: The path to the model file.
+- config_path: The path to the configuration file.
+- device: The type of device, default is 'auto'. Must be one of ['auto', 'cuda', 'mps', 'cpu']
+- device_ids: List of device IDs, default is [0].
+- output_format: The output audio format, default is 'wav'. Must be one of ['wav', 'flac', 'mp3']
+- use_tta: Whether to use TTA, default is False. Using TTA will triple the processing time with a little bit improvement in quality.
+- store_dirs: Storage directories, can be a single folder path or a dictionary with instrument keys.
+- audio_params: Audio parameters including wav_bit_depth, flac_bit_depth, and mp3_bit_rate. Default is {"wav_bit_depth": "FLOAT", "flac_bit_depth": "PCM_24", "mp3_bit_rate": "320k"}.
+- logger: Logger instance. Default is pymss.get_separation_logger()
+- debug: Whether to enable debug mode, default is False.
+- inference_params: Inference parameters including batch_size, num_overlap, chunk_size, and normalize. Default is all None (means all params are depended on the config file).
+
+## Contributing
+Contributions are welcome! 

pymss-1.0/pymss/__init__.py

@@ -0,0 +1,2 @@
+from .separator import MSSeparator
+from .logger import get_separation_logger

pymss-1.0/pymss/logger.py

@@ -0,0 +1,93 @@
+import logging
+import os
+from colorama import Fore, Style, init
+from datetime import datetime
+
+init(autoreset=True)
+
+MAX_LOG = 100
+LOG_DIR = "logs"
+
+class ColorFormatter(logging.Formatter):
+    def format(self, record):
+        record.pathname = os.path.relpath(record.pathname)
+        log_msg = super().format(record)
+
+        if record.levelname == "INFO":
+            log_msg = log_msg.replace("INFO", f"{Fore.GREEN}INFO{Style.RESET_ALL}")
+        elif record.levelname == "DEBUG":
+            log_msg = log_msg.replace("DEBUG", f"{Fore.BLUE}DEBUG{Style.RESET_ALL}")
+        elif record.levelname == "WARNING":
+            log_msg = log_msg.replace("WARNING", f"{Fore.YELLOW}WARNING{Style.RESET_ALL}")
+        elif record.levelname == "ERROR":
+            log_msg = log_msg.replace("ERROR", f"{Fore.RED}ERROR{Style.RESET_ALL}")
+        elif record.levelname == "CRITICAL":
+            log_msg = log_msg.replace("CRITICAL", f"{Fore.MAGENTA}CRITICAL{Style.RESET_ALL}")
+
+        return log_msg
+
+
+def manage_log_files(log_dir, max_log):
+    log_files = [f for f in os.listdir(log_dir) if f.endswith(".log")]
+
+    def parse_date(filename):
+        for fmt in ("%Y-%m-%d", "%Y-%m-%d_%H-%M-%S"):
+            try:
+                return datetime.strptime(filename.split(".")[0], fmt)
+            except ValueError:
+                continue
+        return datetime.min
+
+    log_files = sorted(log_files, key=parse_date)
+
+    while len(log_files) > max_log:
+        try:
+            oldest_file = log_files.pop(0)
+            os.remove(os.path.join(log_dir, oldest_file))
+        except: pass
+
+
+def set_log_level(logger, level):
+    logger.console_handler.setLevel(level)
+
+
+def get_separation_logger(console_level=logging.INFO, enable_file_log=False, max_log=MAX_LOG):
+    logger = logging.getLogger("logger")
+
+    if logger.hasHandlers():
+        return logger
+
+    logger.setLevel(logging.DEBUG)
+
+    console_handler = logging.StreamHandler()
+    console_handler.setLevel(console_level)
+    formatter = ColorFormatter(fmt="%(asctime)s.%(msecs)03d [%(levelname)s] [%(pathname)s:%(lineno)d] %(message)s", datefmt="%H:%M:%S")
+    console_handler.setFormatter(formatter)
+
+    logger.addHandler(console_handler)
+
+    if enable_file_log:
+        os.makedirs(LOG_DIR, exist_ok=True)
+        log_filename = datetime.now().strftime("%Y-%m-%d_%H-%M-%S.log")
+        file_path = os.path.join(LOG_DIR, log_filename)
+
+        file_handler = logging.FileHandler(file_path, mode='a', encoding='utf-8')
+        file_handler.setLevel(logging.DEBUG)
+        file_formatter = logging.Formatter(fmt="%(asctime)s.%(msecs)03d [%(levelname)s] [%(pathname)s:%(lineno)d] %(message)s", datefmt="%H:%M:%S")
+        file_handler.setFormatter(file_formatter)
+        
+        logger.addHandler(file_handler)
+        manage_log_files(LOG_DIR, max_log)
+
+    logger.console_handler = console_handler
+
+    return logger
+
+
+if __name__ == "__main__":
+    logger = get_separation_logger(console_level=logging.INFO, enable_file_log=False)
+    logger.debug("This is a debug message.")
+    logger.info("This is an info message.")
+    logger.warning("This is a warning message.")
+    logger.error("This is an error message.")
+    logger.critical("This is a critical message.")