Merge remote-tracking branch 'remotes/adefossez/main'

README.md

@@ -1,13 +1,13 @@
 # Demucs Music Source Separation
 
-[![Support Ukraine](https://img.shields.io/badge/Support-Ukraine-FFD500?style=flat&labelColor=005BBB)](https://opensource.fb.com/support-ukraine)
 ![tests badge](https://github.com/facebookresearch/demucs/workflows/tests/badge.svg)
 ![linter badge](https://github.com/facebookresearch/demucs/workflows/linter/badge.svg)
 
 
-**Important:** As I am no longer working at Meta, **this repository is not maintained anymore**.
-I've created a fork at [github.com/adefossez/demucs](https://github.com/adefossez/demucs). Note that this project is not actively maintained anymore
-and only important bug fixes will be processed on the new repo. Please do not open issues for feature request or if Demucs doesn't work perfectly for your use case :)
+**This is the officially maintained Demucs** now that I (Alexandre Défossez) have left Meta to join [Kyutai](https://twitter.com/kyutai_labs).
+Note that I'm not actively working on Demucs anymore, so expect slow replies and no new feature for now.
+
+
 
 This is the 4th release of Demucs (v4), featuring Hybrid Transformer based source separation.
 **For the classic Hybrid Demucs (v3):** [Go this commit][demucs_v3].

demucs/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the license found in the
 # LICENSE file in the root directory of this source tree.
 
-__version__ = "4.1.0a2"
+__version__ = "4.1.0a3"

demucs/api.py

@@ -22,6 +22,7 @@
 
 import subprocess
 
+from . import audio_legacy
 import torch as th
 import torchaudio as ta
 

demucs/apply.py

@@ -51,7 +51,7 @@ def __init__(self, models: tp.List[Model],
             assert other.samplerate == first.samplerate
             assert other.audio_channels == first.audio_channels
             if segment is not None:
-                if not isinstance(other, HTDemucs) and segment > other.segment:
+                if not isinstance(other, HTDemucs) or segment <= other.segment:
                     other.segment = segment
 
         self.audio_channels = first.audio_channels

demucs/audio.py

@@ -10,6 +10,7 @@
 import lameenc
 import julius
 import numpy as np
+from . import audio_legacy
 import torch
 import torchaudio as ta
 import typing as tp

demucs/audio_legacy.py

@@ -0,0 +1,17 @@
+# This file is to extend support for torchaudio 2.1
+
+import importlib
+import os
+import sys
+import warnings
+
+if not "torchaudio" in sys.modules:
+    os.environ["TORCHAUDIO_USE_BACKEND_DISPATCHER"] = "0"
+elif os.getenv("TORCHAUDIO_USE_BACKEND_DISPATCHER", default="1") == "1":
+    if sys.modules["torchaudio"].__version__ >= "2.1":
+        os.environ["TORCHAUDIO_USE_BACKEND_DISPATCHER"] = "0"
+        importlib.reload(sys.modules["torchaudio"])
+        warnings.warn(
+            "TORCHAUDIO_USE_BACKEND_DISPATCHER is set to 0 and torchaudio is reloaded.",
+            ImportWarning,
+        )

demucs/hdemucs.py

@@ -776,16 +776,18 @@ def forward(self, mix):
         # demucs issue #435 ##432
         # NOTE: in this case z already is on cpu
         # TODO: remove this when mps supports complex numbers
-        x_is_mps = x.device.type == "mps"
-        if x_is_mps:
+        x_is_mps_xpu = x.device.type in ["mps", "xpu"]
+        x_device = x.device
+        if x_is_mps_xpu:
             x = x.cpu()
 
         zout = self._mask(z, x)
         x = self._ispec(zout, length)
 
         # back to mps device
-        if x_is_mps:
-            x = x.to('mps')
+        if x_is_mps_xpu:
+            x = x.to(x_device)
+
 
         if self.hybrid:
             xt = xt.view(B, S, -1, length)

demucs/htdemucs.py

@@ -629,8 +629,9 @@ def forward(self, mix):
         # demucs issue #435 ##432
         # NOTE: in this case z already is on cpu
         # TODO: remove this when mps supports complex numbers
-        x_is_mps = x.device.type == "mps"
-        if x_is_mps:
+        x_is_mps_xpu = x.device.type in ["mps", "xpu"]
+        x_device = x.device
+        if x_is_mps_xpu:
             x = x.cpu()
 
         zout = self._mask(z, x)
@@ -643,8 +644,8 @@ def forward(self, mix):
             x = self._ispec(zout, length)
 
         # back to mps device
-        if x_is_mps:
-            x = x.to("mps")
+        if x_is_mps_xpu:
+            x = x.to(x_device)
 
         if self.use_train_segment:
             if self.training:

demucs/repitch.py

@@ -9,6 +9,7 @@
 import subprocess as sp
 import tempfile
 
+from . import audio_legacy
 import torch
 import torchaudio as ta
 

demucs/separate.py

@@ -41,7 +41,13 @@ def get_parser():
                         'Default is "{track}/{stem}.{ext}".')
     parser.add_argument("-d",
                         "--device",
-                        default="cuda" if th.cuda.is_available() else "cpu",
+                        default=(
+                            "cuda"
+                            if th.cuda.is_available()
+                            else "mps"
+                            if th.backends.mps.is_available()
+                            else "cpu"
+                        ),
                         help="Device to use, default is cuda if available else cpu")
     parser.add_argument("--shifts",
                         default=1,

demucs/spec.py

@@ -11,8 +11,8 @@
 def spectro(x, n_fft=512, hop_length=None, pad=0):
     *other, length = x.shape
     x = x.reshape(-1, length)
-    is_mps = x.device.type == 'mps'
-    if is_mps:
+    is_mps_xpu = x.device.type in ['mps', 'xpu']
+    if is_mps_xpu:
         x = x.cpu()
     z = th.stft(x,
                 n_fft * (1 + pad),
@@ -32,8 +32,8 @@ def ispectro(z, hop_length=None, length=None, pad=0):
     n_fft = 2 * freqs - 2
     z = z.view(-1, freqs, frames)
     win_length = n_fft // (1 + pad)
-    is_mps = z.device.type == 'mps'
-    if is_mps:
+    is_mps_xpu = z.device.type in ['mps', 'xpu']
+    if is_mps_xpu:
         z = z.cpu()
     x = th.istft(z,
                  n_fft,

demucs/train.py

@@ -15,6 +15,7 @@
 import hydra
 from hydra.core.global_hydra import GlobalHydra
 from omegaconf import OmegaConf
+from . import audio_legacy
 import torch
 from torch import nn
 import torchaudio

demucs/wav.py

@@ -15,6 +15,7 @@
 
 import musdb
 import julius
+from . import audio_legacy
 import torch as th
 from torch import distributed
 import torchaudio as ta

docs/release.md

@@ -1,6 +1,6 @@
 # Release notes for Demucs
 
-## V4.1.0a1, TBD
+## V4.1.0a, TBD
 
 Get models list
 
@@ -14,6 +14,8 @@ Added `--other-method`: method to get `no_{STEM}`, add up all the other stems (a
 
 Added type `HTDemucs` to type alias `AnyModel`.
 
+Improving recent torchaudio versions support (Thanks @CarlGao4) 
+
 ## V4.0.1, 8th of September 2023
 
 **From this version, Python 3.7 is no longer supported. This is not a problem since the latest PyTorch 2.0.0 no longer support it either.**

requirements.txt

@@ -13,7 +13,7 @@ openunmix
 pyyaml
 submitit
 torch>=1.8.1
-torchaudio>=0.8,<2.1
+torchaudio>=0.8,<2.2
 tqdm
 treetable
 soundfile>=0.10.3;sys_platform=="win32"

requirements_minimal.txt

@@ -6,5 +6,5 @@ lameenc>=1.2
 openunmix
 pyyaml
 torch>=1.8.1
-torchaudio>=0.8,<2.1
+torchaudio>=0.8,<2.2
 tqdm