Add files via upload

inference_demucs.py

@@ -1,37 +1,37 @@
-import os
-from pathlib import Path
-import os.path
 from datetime import datetime
-import pydub
-import shutil
-from random import randrange
-#MDX-Net
-#----------------------------------------
-import soundfile as sf
-import torch
-import numpy as np
-
-from demucs.pretrained import get_model as _gm
-from demucs.hdemucs import HDemucs
 from demucs.apply import BagOfModels, apply_model
-from demucs.audio import AudioFile
+from demucs.hdemucs import HDemucs
-
+from demucs.model_v2 import Demucs
-import time
+from demucs.pretrained import get_model as _gm
-import os
+from demucs.tasnet_v2 import ConvTasNet
-from tqdm import tqdm
+from demucs.utils import apply_model_v1
-import warnings
+from demucs.utils import apply_model_v2
-import sys
+from diffq import DiffQuantizer
-import librosa
-import psutil
-#----------------------------------------
 from lib_v5 import spec_utils
 from lib_v5.model_param_init import ModelParameters
-import torch
+from pathlib import Path
-
+from random import randrange
-# Command line text parsing and widget manipulation
+from tqdm import tqdm
-import tkinter as tk
+import gzip
-import traceback  # Error Message Recent Calls
+import io
+import librosa
+import numpy as np
+import os
+import os
+import os.path
+import psutil
+import pydub
+import shutil
+import soundfile as sf
+import sys
+import time
 import time  # Timer
+import tkinter as tk
+import torch
+import torch.hub
+import traceback  # Error Message Recent Calls
+import warnings
+import zlib
     
 class Predictor():        
     def __init__(self):
@@ -46,40 +46,62 @@ class Predictor():
         if data['gpu'] == -1:
             device = torch.device('cpu')
         
-        self.demucs = HDemucs(sources=["drums", "bass", "other", "vocals"])
+        if demucs_model_version == 'v1':
-        widget_text.write(base_text + 'Loading Demucs model... ')
+            load_from = "models/Demucs_Models/"f"{demucs_model_set_name}"
-        update_progress(**progress_kwargs,
+            if str(load_from).endswith(".gz"):
-        step=0.05)   
+                load_from = gzip.open(load_from, "rb")
-        path_d = Path('models/Demucs_Models')
+            klass, args, kwargs, state = torch.load(load_from)
-        print('What Demucs model was chosen? ', data['DemucsModel'])
+            self.demucs = klass(*args, **kwargs)
-        self.demucs = _gm(name=data['DemucsModel'], repo=path_d)
+            widget_text.write(base_text + 'Loading Demucs v1 model... ')
-        widget_text.write('Done!\n')
+            update_progress(**progress_kwargs,
-        if 'UVR' in data['DemucsModel']:
+            step=0.05)   
-            widget_text.write(base_text + "2 stem model selected.\n")
+            self.demucs.to(device) 
-        if isinstance(self.demucs, BagOfModels):
+            self.demucs.load_state_dict(state)
-            widget_text.write(base_text + f"Selected model is a bag of {len(self.demucs.models)} models.\n") 
+            widget_text.write('Done!\n')
-            
+            if not data['segment'] == 'None':
-        if data['segment'] == 'None':
+                widget_text.write(base_text + 'Segments is only available in Demucs v3. Please use \"Chunks\" instead.\n')
-            segment = None
-            if isinstance(self.demucs, BagOfModels):
-                if segment is not None:
-                    for sub in self.demucs.models:
-                        sub.segment = segment
             else:
-                if segment is not None:
+                pass
-                    sub.segment = segment
+                
-        else:
+        if demucs_model_version == 'v2':
-            try:
+            if '48' in demucs_model_set_name:
-                segment = int(data['segment'])
+                channels=48
-                if isinstance(self.demucs, BagOfModels):
+            elif 'unittest' in demucs_model_set_name:
-                    if segment is not None:
+                channels=4
-                        for sub in self.demucs.models:
+            else:
-                            sub.segment = segment
+                channels=64
-                else:
+                
-                    if segment is not None:
+            if 'tasnet' in demucs_model_set_name:
-                        sub.segment = segment
+                self.demucs = ConvTasNet(sources=["drums", "bass", "other", "vocals"], X=10)
-                widget_text.write(base_text + "Segments set to "f"{segment}.\n")
+            else:
-            except:
+                self.demucs = Demucs(sources=["drums", "bass", "other", "vocals"], channels=channels)
+            widget_text.write(base_text + 'Loading Demucs v2 model... ')
+            update_progress(**progress_kwargs,
+            step=0.05)   
+            self.demucs.to(device) 
+            self.demucs.load_state_dict(torch.load("models/Demucs_Models/"f"{demucs_model_set_name}"))
+            widget_text.write('Done!\n')
+            if not data['segment'] == 'None':
+                widget_text.write(base_text + 'Segments is only available in Demucs v3. Please use \"Chunks\" instead.\n')
+            else:
+                pass
+            self.demucs.eval()
+            
+        if demucs_model_version == 'v3':
+            self.demucs = HDemucs(sources=["drums", "bass", "other", "vocals"])
+            widget_text.write(base_text + 'Loading Demucs model... ')
+            update_progress(**progress_kwargs,
+            step=0.05)   
+            path_d = Path('models/Demucs_Models/v3_repo')
+            #print('What Demucs model was chosen? ', demucs_model_set_name)
+            self.demucs = _gm(name=demucs_model_set_name, repo=path_d)
+            widget_text.write('Done!\n')
+            if 'UVR' in data['DemucsModel']:
+                widget_text.write(base_text + "2 stem model selected.\n")
+            if isinstance(self.demucs, BagOfModels):
+                widget_text.write(base_text + f"Selected model is a bag of {len(self.demucs.models)} models.\n") 
+            
+            if data['segment'] == 'None':
                 segment = None
                 if isinstance(self.demucs, BagOfModels):
                     if segment is not None:
@@ -88,9 +110,29 @@ class Predictor():
                 else:
                     if segment is not None:
                         sub.segment = segment
-                
+            else:
-            self.demucs.to(device)
+                try:
-            self.demucs.eval()
+                    segment = int(data['segment'])
+                    if isinstance(self.demucs, BagOfModels):
+                        if segment is not None:
+                            for sub in self.demucs.models:
+                                sub.segment = segment
+                    else:
+                        if segment is not None:
+                            sub.segment = segment
+                    widget_text.write(base_text + "Segments set to "f"{segment}.\n")
+                except:
+                    segment = None
+                    if isinstance(self.demucs, BagOfModels):
+                        if segment is not None:
+                            for sub in self.demucs.models:
+                                sub.segment = segment
+                    else:
+                        if segment is not None:
+                            sub.segment = segment
+                    
+                self.demucs.to(device)
+                self.demucs.eval()
             
         update_progress(**progress_kwargs,
         step=0.1)
@@ -646,7 +688,12 @@ class Predictor():
             if end == samples:
                 break
         
-        sources = self.demix_demucs(segmented_mix, margin_size=margin)
+        if demucs_model_version == 'v1':
+            sources = self.demix_demucs_v1(segmented_mix, margin_size=margin)
+        if demucs_model_version == 'v2':
+            sources = self.demix_demucs_v2(segmented_mix, margin_size=margin)
+        if demucs_model_version == 'v3':
+            sources = self.demix_demucs(segmented_mix, margin_size=margin)
 
         return sources
     
@@ -683,31 +730,94 @@ class Predictor():
         sources = np.concatenate(sources, axis=-1)
         widget_text.write('Done!\n')
         return sources
+    
+    def demix_demucs_v1(self, mix, margin_size):
+        processed = {}
+        demucsitera = len(mix)
+        demucsitera_calc = demucsitera * 2
+        gui_progress_bar_demucs = 0
+        widget_text.write(base_text + "Running Demucs v1 Inference...\n")
+        widget_text.write(base_text + "Processing "f"{len(mix)} slices... ")
+        print(' Running Demucs Inference...')
+        for nmix in mix:
+            gui_progress_bar_demucs += 1
+            update_progress(**progress_kwargs,
+                step=(0.35 + (1.05/demucsitera_calc * gui_progress_bar_demucs)))
+            cmix = mix[nmix]
+            cmix = torch.tensor(cmix, dtype=torch.float32)
+            ref = cmix.mean(0)        
+            cmix = (cmix - ref.mean()) / ref.std()
+            with torch.no_grad():
+                sources = apply_model_v1(self.demucs, cmix.to(device), split=split_mode, shifts=shift_set)
+            sources = (sources * ref.std() + ref.mean()).cpu().numpy()
+            sources[[0,1]] = sources[[1,0]]
+
+            start = 0 if nmix == 0 else margin_size
+            end = None if nmix == list(mix.keys())[::-1][0] else -margin_size
+            if margin_size == 0:
+                end = None
+            processed[nmix] = sources[:,:,start:end].copy()
+
+        sources = list(processed.values())
+        sources = np.concatenate(sources, axis=-1)
+        widget_text.write('Done!\n')
+        return sources
+    
+    def demix_demucs_v2(self, mix, margin_size):
+        processed = {}
+        demucsitera = len(mix)
+        demucsitera_calc = demucsitera * 2
+        gui_progress_bar_demucs = 0
+        widget_text.write(base_text + "Running Demucs v2 Inference...\n")
+        widget_text.write(base_text + "Processing "f"{len(mix)} slices... ")
+        print(' Running Demucs Inference...')
+        for nmix in mix:
+            gui_progress_bar_demucs += 1
+            update_progress(**progress_kwargs,
+                step=(0.35 + (1.05/demucsitera_calc * gui_progress_bar_demucs)))
+            cmix = mix[nmix]
+            cmix = torch.tensor(cmix, dtype=torch.float32)
+            ref = cmix.mean(0)        
+            cmix = (cmix - ref.mean()) / ref.std()
+            shift_set = 0
+            with torch.no_grad():
+                sources = apply_model_v2(self.demucs, cmix.to(device), split=split_mode, overlap=overlap_set, shifts=shift_set)
+            sources = (sources * ref.std() + ref.mean()).cpu().numpy()
+            sources[[0,1]] = sources[[1,0]]
+
+            start = 0 if nmix == 0 else margin_size
+            end = None if nmix == list(mix.keys())[::-1][0] else -margin_size
+            if margin_size == 0:
+                end = None
+            processed[nmix] = sources[:,:,start:end].copy()
+
+        sources = list(processed.values())
+        sources = np.concatenate(sources, axis=-1)
+        widget_text.write('Done!\n')
+        return sources
         
 data = {
-    # Paths
+    'audfile': True,
-    'input_paths': None,
-    'export_path': None,
-    'saveFormat': 'Wav',
-    # Processing Options
-    'demucsmodel': True,
-    'gpu': -1,
     'chunks_d': 'Full',
-    'settest': False,
-    'voc_only_b': False,
-    'inst_only_b': False,
-    'overlap_b': 0.25,
-    'shifts_b': 2,
-    'segment': 'None',
-    'margin': 44100,
-    'split_mode': False,
-    'normalize': False,
     'compensate': 1.03597672895,
     'demucs_stems': 'All Stems',
     'DemucsModel': 'mdx_extra',
-    'audfile': True,
+    'demucsmodel': True,
-    'wavtype': 'PCM_16',
+    'export_path': None,
+    'gpu': -1,
+    'input_paths': None,
+    'inst_only_b': False,
+    'margin': 44100,
     'mp3bit': '320k',
+    'normalize': False,
+    'overlap_b': 0.25,
+    'saveFormat': 'Wav',
+    'segment': 'None',
+    'settest': False,
+    'shifts_b': 2,
+    'split_mode': False,
+    'voc_only_b': False,
+    'wavtype': 'PCM_16',
 }
 default_chunks = data['chunks_d']
 
@@ -756,6 +866,8 @@ def main(window: tk.Wm, text_widget: tk.Text, button_widget: tk.Button, progress
     global shift_set
     global source_val
     global split_mode
+    global demucs_model_set_name
+    global demucs_model_version
     
     global wav_type_set
     global flac_type_set
@@ -817,6 +929,69 @@ def main(window: tk.Wm, text_widget: tk.Text, button_widget: tk.Button, progress
     progress_var.set(0)
     text_widget.clear()
     button_widget.configure(state=tk.DISABLED)  # Disable Button
+    
+    
+    if data['DemucsModel'] == "Tasnet v1":
+        demucs_model_set_name = 'tasnet.th'
+        demucs_model_version = 'v1'
+    elif data['DemucsModel'] == "Tasnet_extra v1":
+        demucs_model_set_name = 'tasnet_extra.th'
+        demucs_model_version = 'v1'
+    elif data['DemucsModel'] == "Demucs v1":
+        demucs_model_set_name = 'demucs.th'
+        demucs_model_version = 'v1'
+    elif data['DemucsModel'] == "Demucs v1.gz":
+        demucs_model_set_name = 'demucs.th.gz'
+        demucs_model_version = 'v1'
+    elif data['DemucsModel'] == "Demucs_extra v1":
+        demucs_model_set_name = 'demucs_extra.th'
+        demucs_model_version = 'v1'
+    elif data['DemucsModel'] == "Demucs_extra v1.gz":
+        demucs_model_set_name = 'demucs_extra.th.gz'
+        demucs_model_version = 'v1'
+    elif data['DemucsModel'] == "Light v1":
+        demucs_model_set_name = 'light.th'
+        demucs_model_version = 'v1'
+    elif data['DemucsModel'] == "Light v1.gz":
+        demucs_model_set_name = 'light.th.gz'
+        demucs_model_version = 'v1'
+    elif data['DemucsModel'] == "Light_extra v1":
+        demucs_model_set_name = 'light_extra.th'
+        demucs_model_version = 'v1'
+    elif data['DemucsModel'] == "Light_extra v1.gz":
+        demucs_model_set_name = 'light_extra.th.gz'
+        demucs_model_version = 'v1'
+    elif data['DemucsModel'] == "Tasnet v2":
+        demucs_model_set_name = 'tasnet-beb46fac.th'
+        demucs_model_version = 'v2'
+    elif data['DemucsModel'] == "Tasnet_extra v2":
+        demucs_model_set_name = 'tasnet_extra-df3777b2.th'
+        demucs_model_version = 'v2'
+    elif data['DemucsModel'] == "Demucs48_hq v2":
+        demucs_model_set_name = 'demucs48_hq-28a1282c.th'
+        demucs_model_version = 'v2'
+    elif data['DemucsModel'] == "Demucs v2":
+        demucs_model_set_name = 'demucs-e07c671f.th'
+        demucs_model_version = 'v2'
+    elif data['DemucsModel'] == "Demucs_extra v2":
+        demucs_model_set_name = 'demucs_extra-3646af93.th'
+        demucs_model_version = 'v2'
+    elif data['DemucsModel'] == "Demucs_unittest v2":
+        demucs_model_set_name = 'demucs_unittest-09ebc15f.th'
+        demucs_model_version = 'v2'
+    elif '.ckpt' in data['DemucsModel'] and 'v2' in data['DemucsModel']:
+        demucs_model_set_name = data['DemucsModel']
+        demucs_model_version = 'v2'
+    elif '.ckpt' in data['DemucsModel'] and 'v1' in data['DemucsModel']:
+        demucs_model_set_name = data['DemucsModel']
+        demucs_model_version = 'v1'
+    elif '.gz' in data['DemucsModel']:
+        demucs_model_set_name = data['DemucsModel']
+        demucs_model_version = 'v1'
+    else:
+        demucs_model_set_name = data['DemucsModel']
+        demucs_model_version = 'v3'
+        
 
     try:    #Load File(s)
         for file_num, music_file in tqdm(enumerate(data['input_paths'], start=1)):
@@ -880,7 +1055,10 @@ def main(window: tk.Wm, text_widget: tk.Text, button_widget: tk.Button, progress
             channel_set = int(data['channel'])
             margin_set = int(data['margin'])
             shift_set = int(data['shifts_b'])
+            
             split_mode = data['split_mode']
+                
+            #print('Split? ', split_mode)
             
             def determinemusicfileFolderName():
                 """

inference_v5.py

@@ -1,34 +1,31 @@
-import os
+from collections import defaultdict
-import importlib
+from datetime import datetime
-import pydub
-import shutil
-import hashlib
-
-import cv2
-import librosa
-import math
-import numpy as np
-import soundfile as sf
-from tqdm import tqdm
-
-from demucs.pretrained import get_model as _gm
-from demucs.hdemucs import HDemucs
 from demucs.apply import BagOfModels, apply_model
-from pathlib import Path
+from demucs.hdemucs import HDemucs
-from models import stft, istft
+from demucs.pretrained import get_model as _gm
-
 from lib_v5 import dataset
 from lib_v5 import spec_utils
 from lib_v5.model_param_init import ModelParameters
-import torch
+from models import stft, istft
-from datetime import datetime
+from pathlib import Path
-
-# Command line text parsing and widget manipulation
-from collections import defaultdict
-import tkinter as tk
-import traceback  # Error Message Recent Calls
-import time  # Timer
 from random import randrange
+from tqdm import tqdm
+from tkinter import filedialog
+import lib_v5.filelist
+import cv2
+import hashlib
+import importlib
+import librosa
+import math
+import numpy as np
+import os
+import pydub
+import shutil
+import soundfile as sf
+import time  # Timer
+import tkinter as tk
+import torch
+import traceback  # Error Message Recent Calls
 
 class VocalRemover(object):
     
@@ -40,35 +37,31 @@ class VocalRemover(object):
         # self.offset = model.offset
         
 data = {
-    # Paths
-    'input_paths': None,
-    'export_path': None,
-    'saveFormat': 'wav',
-    # Processing Options
-    'gpu': -1,
-    'postprocess': True,
-    'tta': True,
-    'output_image': True,
-    'voc_only': False,
-    'inst_only': False,
-    # Models
-    'instrumentalModel': None,
-    'useModel': None,
-    # Constants
-    'window_size': 512,
     'agg': 10,
-    'high_end_process': 'mirroring',
-    'ModelParams': 'Auto',
     'demucsmodel_sel_VR': 'UVR_Demucs_Model_1',
-    'overlap': 0.5,
-    'shifts': 0,
-    'segment': 'None',
-    'split_mode': False,
-    'normalize': False,
     'demucsmodelVR': True,
-    'wavtype': 'PCM_16',
+    'export_path': None,
+    'gpu': -1,
+    'high_end_process': 'mirroring',
+    'input_paths': None,
+    'inst_only': False,
+    'instrumentalModel': None,
+    'ModelParams': 'Auto',
     'mp3bit': '320k',
+    'normalize': False,
+    'output_image': True,
+    'overlap': 0.5,
+    'postprocess': True,
+    'saveFormat': 'wav',
+    'segment': 'None',
     'settest': False,
+    'shifts': 0,
+    'split_mode': False,
+    'tta': True,
+    'useModel': None,
+    'voc_only': False,
+    'wavtype': 'PCM_16',
+    'window_size': 512,
 }
 
 default_window_size = data['window_size']
@@ -144,7 +137,7 @@ def main(window: tk.Wm, text_widget: tk.Text, button_widget: tk.Button, progress
     
     nn_arch_sizes = [
         31191, # default
-        33966, 123821, 123812, 537238 # custom
+        33966, 123821, 123812, 129605, 537238 # custom
     ]
     
     nn_architecture = list('{}KB'.format(s) for s in nn_arch_sizes)
@@ -492,7 +485,7 @@ def main(window: tk.Wm, text_widget: tk.Text, button_widget: tk.Button, progress
                                 return 
                 
                         #Load Model      
-                        text_widget.write(base_text + 'Loading models...')
+                        text_widget.write(base_text + 'Loading model...')
                         
                         model_size = math.ceil(os.stat(data['instrumentalModel']).st_size / 1024)
                         nn_architecture = '{}KB'.format(min(nn_arch_sizes, key=lambda x:abs(x-model_size)))
@@ -504,212 +497,77 @@ def main(window: tk.Wm, text_widget: tk.Text, button_widget: tk.Button, progress
                         ModelName=(data['instrumentalModel'])
 
                         #Package Models
-                        
+                        text_widget.write('Done!\n')
-                        model_hash = hashlib.md5(open(ModelName,'rb').read()).hexdigest()
-                        print(model_hash)
-                        
-                        #v5 Models
-                        
-                        if model_hash == '47939caf0cfe52a0e81442b85b971dfd':  
-                            model_params_auto=str('lib_v5/modelparams/4band_44100.json')
-                            param_name_auto=str('4band_44100')
-                        if model_hash == '4e4ecb9764c50a8c414fee6e10395bbe':  
-                            model_params_auto=str('lib_v5/modelparams/4band_v2.json')
-                            param_name_auto=str('4band_v2')
-                        if model_hash == 'e60a1e84803ce4efc0a6551206cc4b71':  
-                            model_params_auto=str('lib_v5/modelparams/4band_44100.json')
-                            param_name_auto=str('4band_44100')
-                        if model_hash == 'a82f14e75892e55e994376edbf0c8435':  
-                            model_params_auto=str('lib_v5/modelparams/4band_44100.json')
-                            param_name_auto=str('4band_44100')
-                        if model_hash == '6dd9eaa6f0420af9f1d403aaafa4cc06':   
-                            model_params_auto=str('lib_v5/modelparams/4band_v2_sn.json')
-                            param_name_auto=str('4band_v2_sn')
-                        if model_hash == '5c7bbca45a187e81abbbd351606164e5':    
-                            model_params_auto=str('lib_v5/modelparams/3band_44100_msb2.json')
-                            param_name_auto=str('3band_44100_msb2')
-                        if model_hash == 'd6b2cb685a058a091e5e7098192d3233':    
-                            model_params_auto=str('lib_v5/modelparams/3band_44100_msb2.json')
-                            param_name_auto=str('3band_44100_msb2')
-                        if model_hash == 'c1b9f38170a7c90e96f027992eb7c62b': 
-                            model_params_auto=str('lib_v5/modelparams/4band_44100.json')
-                            param_name_auto=str('4band_44100')
-                        if model_hash == 'c3448ec923fa0edf3d03a19e633faa53':  
-                            model_params_auto=str('lib_v5/modelparams/4band_44100.json')
-                            param_name_auto=str('4band_44100')
-                        if model_hash == '68aa2c8093d0080704b200d140f59e54':  
-                            model_params_auto=str('lib_v5/modelparams/3band_44100.json')
-                            param_name_auto=str('3band_44100.json')
-                        if model_hash == 'fdc83be5b798e4bd29fe00fe6600e147':  
-                            model_params_auto=str('lib_v5/modelparams/3band_44100_mid.json')
-                            param_name_auto=str('3band_44100_mid.json')
-                        if model_hash == '2ce34bc92fd57f55db16b7a4def3d745':  
-                            model_params_auto=str('lib_v5/modelparams/3band_44100_mid.json')
-                            param_name_auto=str('3band_44100_mid.json')
-                        if model_hash == '52fdca89576f06cf4340b74a4730ee5f':  
-                            model_params_auto=str('lib_v5/modelparams/4band_44100.json')
-                            param_name_auto=str('4band_44100.json')
-                        if model_hash == '41191165b05d38fc77f072fa9e8e8a30':  
-                            model_params_auto=str('lib_v5/modelparams/4band_44100.json')
-                            param_name_auto=str('4band_44100.json')
-                        if model_hash == '89e83b511ad474592689e562d5b1f80e':  
-                            model_params_auto=str('lib_v5/modelparams/2band_32000.json')
-                            param_name_auto=str('2band_32000.json')
-                        if model_hash == '0b954da81d453b716b114d6d7c95177f':  
-                            model_params_auto=str('lib_v5/modelparams/2band_32000.json')
-                            param_name_auto=str('2band_32000.json')
-                            
-                        #v4 Models
-                            
-                        if model_hash == '6a00461c51c2920fd68937d4609ed6c8':  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr16000_hl512.json')
-                            param_name_auto=str('1band_sr16000_hl512')
-                        if model_hash == '0ab504864d20f1bd378fe9c81ef37140':  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr32000_hl512.json')
-                            param_name_auto=str('1band_sr32000_hl512')
-                        if model_hash == '7dd21065bf91c10f7fccb57d7d83b07f':  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr32000_hl512.json')
-                            param_name_auto=str('1band_sr32000_hl512')
-                        if model_hash == '80ab74d65e515caa3622728d2de07d23':  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr32000_hl512.json')
-                            param_name_auto=str('1band_sr32000_hl512')
-                        if model_hash == 'edc115e7fc523245062200c00caa847f':  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr33075_hl384.json')
-                            param_name_auto=str('1band_sr33075_hl384')
-                        if model_hash == '28063e9f6ab5b341c5f6d3c67f2045b7':  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr33075_hl384.json')
-                            param_name_auto=str('1band_sr33075_hl384')
-                        if model_hash == 'b58090534c52cbc3e9b5104bad666ef2':  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr44100_hl512.json')
-                            param_name_auto=str('1band_sr44100_hl512')
-                        if model_hash == '0cdab9947f1b0928705f518f3c78ea8f':  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr44100_hl512.json')
-                            param_name_auto=str('1band_sr44100_hl512')
-                        if model_hash == 'ae702fed0238afb5346db8356fe25f13':  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr44100_hl1024.json')
-                            param_name_auto=str('1band_sr44100_hl1024')
-                        
-                        #User Models
-  
-                        #1 Band
-                        if '1band_sr16000_hl512' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr16000_hl512.json')
-                            param_name_auto=str('1band_sr16000_hl512')
-                        if '1band_sr32000_hl512' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr32000_hl512.json')
-                            param_name_auto=str('1band_sr32000_hl512')
-                        if '1band_sr33075_hl384' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr33075_hl384.json')
-                            param_name_auto=str('1band_sr33075_hl384')
-                        if '1band_sr44100_hl256' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr44100_hl256.json')
-                            param_name_auto=str('1band_sr44100_hl256')
-                        if '1band_sr44100_hl512' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr44100_hl512.json')
-                            param_name_auto=str('1band_sr44100_hl512')
-                        if '1band_sr44100_hl1024' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/1band_sr44100_hl1024.json')
-                            param_name_auto=str('1band_sr44100_hl1024')
-                            
-                        #2 Band
-                        if '2band_44100_lofi' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/2band_44100_lofi.json')
-                            param_name_auto=str('2band_44100_lofi')
-                        if '2band_32000' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/2band_32000.json')
-                            param_name_auto=str('2band_32000')
-                        if '2band_48000' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/2band_48000.json')
-                            param_name_auto=str('2band_48000')
-                            
-                        #3 Band   
-                        if '3band_44100' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/3band_44100.json')
-                            param_name_auto=str('3band_44100')
-                        if '3band_44100_mid' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/3band_44100_mid.json')
-                            param_name_auto=str('3band_44100_mid')
-                        if '3band_44100_msb2' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/3band_44100_msb2.json')
-                            param_name_auto=str('3band_44100_msb2')
-                            
-                        #4 Band    
-                        if '4band_44100' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/4band_44100.json')
-                            param_name_auto=str('4band_44100')
-                        if '4band_44100_mid' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/4band_44100_mid.json')
-                            param_name_auto=str('4band_44100_mid')
-                        if '4band_44100_msb' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/4band_44100_msb.json')
-                            param_name_auto=str('4band_44100_msb')
-                        if '4band_44100_msb2' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/4band_44100_msb2.json')
-                            param_name_auto=str('4band_44100_msb2')
-                        if '4band_44100_reverse' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/4band_44100_reverse.json')
-                            param_name_auto=str('4band_44100_reverse')
-                        if '4band_44100_sw' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/4band_44100_sw.json') 
-                            param_name_auto=str('4band_44100_sw')
-                        if '4band_v2' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/4band_v2.json')
-                            param_name_auto=str('4band_v2')
-                        if '4band_v2_sn' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/4band_v2_sn.json')
-                            param_name_auto=str('4band_v2_sn')
-                        if 'tmodelparam' in ModelName:  
-                            model_params_auto=str('lib_v5/modelparams/tmodelparam.json')
-                            param_name_auto=str('User Model Param Set')
-  
-                        text_widget.write(' Done!\n')
-                        
                         
                         if data['ModelParams'] == 'Auto':
-                            param_name = param_name_auto
+                            model_hash = hashlib.md5(open(ModelName,'rb').read()).hexdigest()
-                            model_params_d = model_params_auto
+                            model_params = []   
+                            model_params = lib_v5.filelist.provide_model_param_hash(model_hash)
+                            print(model_params)
+                            if model_params[0] == 'Not Found Using Hash':
+                                model_params = []   
+                                model_params = lib_v5.filelist.provide_model_param_name(ModelName)
+                            if model_params[0] == 'Not Found Using Name':
+                                text_widget.write(base_text + f'Unable to set model parameters automatically with the selected model.\n')
+                                confirm = tk.messagebox.askyesno(title='Unrecognized Model Detected',
+                                        message=f'\nThe application could not automatically set the model param for the selected model.\n\n' + 
+                                        f'Would you like to select the model param file for this model?\n\n')
+                                
+                                if confirm:
+                                    model_param_selection = filedialog.askopenfilename(initialdir='lib_v5/modelparams', 
+                                                                            title=f'Select Model Param', 
+                                                                            filetypes=[("Model Param", "*.json")])
+                                    
+                                    model_param_file_path = str(model_param_selection)
+                                    model_param_file = os.path.splitext(os.path.basename(model_param_file_path))[0] + '.json'
+                                    model_params = [model_param_file_path, model_param_file]
+                                    
+                                    with open(f"lib_v5/filelists/model_cache/vr_param_cache/{model_hash}.txt", 'w') as f:
+                                        f.write(model_param_file)
+                                        
+                                    
+                                    if model_params[0] == '':
+                                        text_widget.write("\n" + base_text + f'Separation failed for the following audio file:\n')
+                                        text_widget.write(base_text + f'"{os.path.basename(music_file)}"\n')
+                                        text_widget.write(f'\nError Received:\n\n')
+                                        text_widget.write(f'Model parameters are missing.\n\n')
+                                        text_widget.write(f'Please check the following:\n')
+                                        text_widget.write(f'1. Make sure the model is still present.\n')
+                                        text_widget.write(f'2. If you are running a model that was not originally included in this package, \nplease append the modelparam name to the model name.\n')
+                                        text_widget.write(f'  - Example if using \"4band_v2.json\" modelparam: \"model_4band_v2.pth\"\n\n')
+                                        text_widget.write(f'Please address this and try again.\n\n')
+                                        text_widget.write(f'Time Elapsed: {time.strftime("%H:%M:%S", time.gmtime(int(time.perf_counter() - stime)))}')
+                                        torch.cuda.empty_cache()
+                                        progress_var.set(0)
+                                        button_widget.configure(state=tk.NORMAL)  # Enable Button
+                                        return
+                                        
+                                    else:
+                                        pass
+                                else:
+                                    text_widget.write(base_text + f'Model param not selected.\n')
+                                    text_widget.write("\n" + base_text + f'Separation failed for the following audio file:\n')
+                                    text_widget.write(base_text + f'"{os.path.basename(music_file)}"\n')
+                                    text_widget.write(f'\nError Received:\n\n')
+                                    text_widget.write(f'Model parameters are missing.\n\n')
+                                    text_widget.write(f'Please check the following:\n')
+                                    text_widget.write(f'1. Make sure the model is still present.\n')
+                                    text_widget.write(f'2. If you are running a model that was not originally included in this package, \nplease append the modelparam name to the model name.\n')
+                                    text_widget.write(f'  - Example if using \"4band_v2.json\" modelparam: \"model_4band_v2.pth\"\n\n')
+                                    text_widget.write(f'Please address this and try again.\n\n')
+                                    text_widget.write(f'Time Elapsed: {time.strftime("%H:%M:%S", time.gmtime(int(time.perf_counter() - stime)))}')
+                                    torch.cuda.empty_cache()
+                                    progress_var.set(0)
+                                    button_widget.configure(state=tk.NORMAL)  # Enable Button
+                                    return
+
                         else:
-                            param_name = str(data['ModelParams'])
+                            param = data['ModelParams']
-                            model_params_d = str('lib_v5/modelparams/' + data['ModelParams'])
+                            model_param_file_path = f'lib_v5/modelparams/{param}'
+                            model_params = [model_param_file_path, param]
                         
-                        try:
+                        text_widget.write(base_text + 'Loading assigned model parameters ' + '\"' + model_params[1] + '\"... ')
-                            print('Model Parameters:', model_params_d)
+                        mp = ModelParameters(model_params[0])
-                            text_widget.write(base_text + 'Loading assigned model parameters ' + '\"' + param_name + '\"... ')
-                        except Exception as e:
-                            traceback_text = ''.join(traceback.format_tb(e.__traceback__))
-                            errmessage = f'Traceback Error: "{traceback_text}"\n{type(e).__name__}: "{e}"\n'
-                            text_widget.write("\n" + base_text + f'Separation failed for the following audio file:\n')
-                            text_widget.write(base_text + f'"{os.path.basename(music_file)}"\n')
-                            text_widget.write(f'\nError Received:\n\n')
-                            text_widget.write(f'Model parameters are missing.\n\n')
-                            text_widget.write(f'Please check the following:\n')
-                            text_widget.write(f'1. Make sure the model is still present.\n')
-                            text_widget.write(f'2. If you are running a model that was not originally included in this package, \nplease append the modelparam name to the model name.\n')
-                            text_widget.write(f'  - Example if using \"4band_v2.json\" modelparam: \"model_4band_v2.pth\"\n\n')
-                            text_widget.write(f'Please address this and try again.\n\n')
-                            text_widget.write(f'Time Elapsed: {time.strftime("%H:%M:%S", time.gmtime(int(time.perf_counter() - stime)))}')
-                            try:
-                                with open('errorlog.txt', 'w') as f:
-                                    f.write(f'Last Error Received:\n\n' +
-                                            f'Error Received while processing "{os.path.basename(music_file)}":\n' + 
-                                            f'Process Method: VR Architecture\n\n' +
-                                            f'Model parameters are missing.\n\n' + 
-                                            f'Please check the following:\n' + 
-                                            f'1. Make sure the model is still present.\n' +
-                                            f'2. If you are running a model that was not originally included in this package, please append the modelparam name to the model name.\n' + 
-                                            f'  - Example if using \"4band_v2.json\" modelparam: \"model_4band_v2.pth\"\n\n' +
-                                            f'Please address this and try again.\n\n' +
-                                            f'Raw error details:\n\n' +
-                                            errmessage + f'\nError Time Stamp: [{datetime.now().strftime("%Y-%m-%d %H:%M:%S")}]\n') 
-                            except:
-                                pass
-                            torch.cuda.empty_cache()
-                            progress_var.set(0)
-                            button_widget.configure(state=tk.NORMAL)  # Enable Button
-                            return
-                        
-                        
-                        mp = ModelParameters(model_params_d)
                         text_widget.write('Done!\n')
                         # -Instrumental-
                         if os.path.isfile(data['instrumentalModel']):
@@ -726,10 +584,8 @@ def main(window: tk.Wm, text_widget: tk.Text, button_widget: tk.Button, progress
 
                         
                         model_name = os.path.basename(data[f'{data["useModel"]}Model'])
-
-                        mp = ModelParameters(model_params_d)
                             
-                        # -Go through the different steps of seperation-
+                        # -Go through the different steps of Separation-
                         # Wave source
                         text_widget.write(base_text + 'Loading audio source...')
                         
@@ -921,12 +777,12 @@ def main(window: tk.Wm, text_widget: tk.Text, button_widget: tk.Button, progress
                             text_widget.write(base_text + 'Loading Demucs model... ')
                             update_progress(**progress_kwargs,
                             step=0.95)   
-                            path_d = Path('models/Demucs_Models')
+                            path_d = Path('models/Demucs_Models/v3_repo')
-                            print('What Demucs model was chosen? ', demucs_model_set)
+                            #print('What Demucs model was chosen? ', demucs_model_set)
                             demucs = _gm(name=demucs_model_set, repo=path_d)
                             text_widget.write('Done!\n')
                             
-                            print('segment: ', data['segment'])
+                            #print('segment: ', data['segment'])
                             
                             if data['segment'] == 'None':
                                 segment = None
@@ -958,7 +814,7 @@ def main(window: tk.Wm, text_widget: tk.Text, button_widget: tk.Button, progress
                                         if segment is not None:
                                             sub.segment = segment
                             
-                            print('segment port-process: ', segment)
+                            #print('segment port-process: ', segment)
                             
                             demucs.cpu()
                             demucs.eval()
@@ -1048,7 +904,7 @@ def main(window: tk.Wm, text_widget: tk.Text, button_widget: tk.Button, progress
                                 bin_image.tofile(f)
            
 
-                        text_widget.write(base_text + 'Completed Seperation!\n\n')
+                        text_widget.write(base_text + 'Completed Separation!\n\n')
     except Exception as e:
         traceback_text = ''.join(traceback.format_tb(e.__traceback__))
         message = f'Traceback Error: "{traceback_text}"\n{type(e).__name__}: "{e}"\n'

models.py

@@ -7,8 +7,6 @@ import librosa
 dim_c = 4
 model_path = 'model'
 
-#n_fft_scale = {'vocals-one':6144, 'vocals-two':7680,'*':2}
-
 class Conv_TDF_net_trim(nn.Module):
     def __init__(self, device, n_fft_scale, dim_f, load, model_name, target_name, 
                  L, dim_t, hop=1024):
@@ -20,9 +18,9 @@ class Conv_TDF_net_trim(nn.Module):
         self.hop = hop
         self.n_bins = self.n_fft//2+1
         self.chunk_size = hop * (self.dim_t-1)
-        self.window = torch.hann_window(window_length=self.n_fft, periodic=True).to(device)
+        self.window = torch.hann_window(window_length=self.n_fft, periodic=False).to(device)
         self.target_name = target_name
-        print(n_fft_scale)
+        #print(n_fft_scale)
         out_c = dim_c*4 if target_name=='*' else dim_c
         self.freq_pad = torch.zeros([1, out_c, self.n_bins-self.dim_f, self.dim_t]).to(device)
         
@@ -61,17 +59,21 @@ def istft(spec, hl):
     return wave
 
 def spec_effects(wave, algorithm='Default', value=None):
-    spec = [stft(wave[0],2048,1024),stft(wave[1],2048,1024)]
+    doubleout = spec = [stft(wave[0],2048,1024),stft(wave[1],2048,1024)]
     if algorithm == 'Min_Mag':
+        doubleout
         v_spec_m = np.where(np.abs(spec[1]) <= np.abs(spec[0]), spec[1], spec[0])
         wave = istft(v_spec_m,1024)
     elif algorithm == 'Max_Mag':
+        doubleout
         v_spec_m = np.where(np.abs(spec[1]) >= np.abs(spec[0]), spec[1], spec[0])
         wave = istft(v_spec_m,1024)
     elif algorithm == 'Default':
+        doubleout
         #wave = [istft(spec[0],1024),istft(spec[1],1024)]
         wave = (wave[1] * value) + (wave[0] * (1-value))
     elif algorithm == 'Invert_p':
+            doubleout
             X_mag = np.abs(spec[0])
             y_mag = np.abs(spec[1])            
             max_mag = np.where(X_mag >= y_mag, X_mag, y_mag)