Use preload_from_hub for models, only upload vocal_separator

.gitignore

@@ -66,7 +66,9 @@ htmlcov/
 
 
 outputs/
-checkpoints/
+# 忽略大部分 checkpoints，只保留 vocal_separator
+checkpoints/*
+!checkpoints/vocal_separator/
 scripts/
 logs/
 output

README.md

@@ -8,6 +8,10 @@ sdk_version: "4.44.1"
 app_file: app.py
 pinned: false
 short_description: Audio-Driven Multi-Person Talking Video Generation
+preload_from_hub:
+  - alibaba-pai/Wan2.1-Fun-V1.1-1.3B-InP
+  - facebook/wav2vec2-base-960h
+  - zzz66/AnyTalker-1.3B
 ---
 
 <div align="center">

app.py

@@ -15,6 +15,7 @@ import random
 import torch
 import torch.distributed as dist
 from PIL import Image
+from huggingface_hub import snapshot_download
 
 # 导入 AnyTalker 相关的模块
 import wan
@@ -23,6 +24,36 @@ from wan.utils.utils import cache_video, str2bool
 from wan.utils.infer_utils import calculate_frame_num_from_audio
 from utils.get_face_bbox import FaceInference
 
+# 获取 HuggingFace 预加载模型的路径
+def get_model_path(repo_id):
+    """获取 HF 模型的本地缓存路径"""
+    try:
+        return snapshot_download(repo_id=repo_id, local_files_only=True)
+    except:
+        # 如果缓存不存在，则下载
+        return snapshot_download(repo_id=repo_id)
+
+# 模型路径（优先使用 HF cache，否则使用本地 checkpoints）
+def get_ckpt_dir():
+    try:
+        return get_model_path("alibaba-pai/Wan2.1-Fun-V1.1-1.3B-InP")
+    except:
+        return "./checkpoints/Wan2.1-Fun-1.3B-Inp"
+
+def get_anytalker_path():
+    try:
+        path = get_model_path("zzz66/AnyTalker-1.3B")
+        return os.path.join(path, "1_3B-single-v1.pth")
+    except:
+        return "./checkpoints/AnyTalker/1_3B-single-v1.pth"
+
+def get_dit_config_path():
+    try:
+        path = get_model_path("zzz66/AnyTalker-1.3B")
+        return os.path.join(path, "config_af2v_1_3B.json")
+    except:
+        return "./checkpoints/AnyTalker/config_af2v_1_3B.json"
+
 
 def str2bool(v):
     """字符串转布尔值工具函数"""
@@ -36,6 +67,14 @@ def str2bool(v):
         raise argparse.ArgumentTypeError('Boolean value expected.')
 
 def _validate_args(args):
+    # 设置模型路径（从 HF cache 或本地 checkpoints）
+    if args.ckpt_dir is None:
+        args.ckpt_dir = get_ckpt_dir()
+    if args.post_trained_checkpoint_path is None:
+        args.post_trained_checkpoint_path = get_anytalker_path()
+    if args.dit_config is None:
+        args.dit_config = get_dit_config_path()
+    
     # Basic check
     assert args.ckpt_dir is not None, "Please specify the checkpoint directory."
     assert args.task in WAN_CONFIGS, f"Unsupport task: {args.task}"
@@ -87,12 +126,12 @@ def _parse_args():
     parser.add_argument(
         "--ckpt_dir",
         type=str,
-        default="./checkpoints/Wan2.1-Fun-1.3B-Inp",
+        default=None,  # 将在运行时通过 get_ckpt_dir() 获取
         help="The path to the checkpoint directory.")
     parser.add_argument(
         "--post_trained_checkpoint_path",
         type=str,
-        default="./checkpoints/AnyTalker/1_3B-single-v1.pth",
+        default=None,  # 将在运行时通过 get_anytalker_path() 获取
         help="The path to the posted-trained checkpoint file.")
     parser.add_argument(
         "--offload_model",
@@ -229,7 +268,7 @@ def _parse_args():
     parser.add_argument(
         "--dit_config",
         type=str,
-        default="./checkpoints/AnyTalker/config_af2v_1_3B.json",
+        default=None,  # 将在运行时通过 get_dit_config_path() 获取
         help="The path to the dit config file.")
     parser.add_argument(
         "--det_thresh",

checkpoints/vocal_separator/Kim_Vocal_2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce74ef3b6a6024ce44211a07be9cf8bc6d87728cc852a68ab34eb8e58cde9c8b
+size 66759214

checkpoints/vocal_separator/download_checks.json

@@ -0,0 +1,289 @@
+{
+    "current_version": "UVR_Patch_10_6_23_4_27",
+    "current_version_ocl": "UVR_Patch_10_6_23_4_27",
+    "current_version_mac": "UVR_Patch_10_6_23_4_27",
+    "current_version_linux": "UVR_Patch_10_6_23_4_27",
+    "vr_download_list": {
+                        "VR Arch Single Model v5: 1_HP-UVR": "1_HP-UVR.pth",
+                        "VR Arch Single Model v5: 2_HP-UVR": "2_HP-UVR.pth",
+                        "VR Arch Single Model v5: 3_HP-Vocal-UVR": "3_HP-Vocal-UVR.pth",
+                        "VR Arch Single Model v5: 4_HP-Vocal-UVR": "4_HP-Vocal-UVR.pth",
+                        "VR Arch Single Model v5: 5_HP-Karaoke-UVR": "5_HP-Karaoke-UVR.pth",
+                        "VR Arch Single Model v5: 6_HP-Karaoke-UVR": "6_HP-Karaoke-UVR.pth",
+                        "VR Arch Single Model v5: 7_HP2-UVR": "7_HP2-UVR.pth",
+                        "VR Arch Single Model v5: 8_HP2-UVR": "8_HP2-UVR.pth",
+                        "VR Arch Single Model v5: 9_HP2-UVR": "9_HP2-UVR.pth",
+                        "VR Arch Single Model v5: 10_SP-UVR-2B-32000-1": "10_SP-UVR-2B-32000-1.pth",
+                        "VR Arch Single Model v5: 11_SP-UVR-2B-32000-2": "11_SP-UVR-2B-32000-2.pth",
+                        "VR Arch Single Model v5: 12_SP-UVR-3B-44100": "12_SP-UVR-3B-44100.pth",
+                        "VR Arch Single Model v5: 13_SP-UVR-4B-44100-1": "13_SP-UVR-4B-44100-1.pth",
+                        "VR Arch Single Model v5: 14_SP-UVR-4B-44100-2": "14_SP-UVR-4B-44100-2.pth",
+                        "VR Arch Single Model v5: 15_SP-UVR-MID-44100-1": "15_SP-UVR-MID-44100-1.pth",
+                        "VR Arch Single Model v5: 16_SP-UVR-MID-44100-2": "16_SP-UVR-MID-44100-2.pth",
+                        "VR Arch Single Model v5: 17_HP-Wind_Inst-UVR": "17_HP-Wind_Inst-UVR.pth",
+                        "VR Arch Single Model v5: UVR-De-Echo-Aggressive by FoxJoy": "UVR-De-Echo-Aggressive.pth",
+                        "VR Arch Single Model v5: UVR-De-Echo-Normal by FoxJoy": "UVR-De-Echo-Normal.pth",
+                        "VR Arch Single Model v5: UVR-DeEcho-DeReverb by FoxJoy": "UVR-DeEcho-DeReverb.pth",
+                        "VR Arch Single Model v5: UVR-DeNoise-Lite by FoxJoy": "UVR-DeNoise-Lite.pth",
+                        "VR Arch Single Model v5: UVR-DeNoise by FoxJoy": "UVR-DeNoise.pth",
+                        "VR Arch Single Model v5: UVR-BVE-4B_SN-44100-1": "UVR-BVE-4B_SN-44100-1.pth",
+                        "VR Arch Single Model v4: MGM_HIGHEND_v4": "MGM_HIGHEND_v4.pth",
+                        "VR Arch Single Model v4: MGM_LOWEND_A_v4": "MGM_LOWEND_A_v4.pth",
+                        "VR Arch Single Model v4: MGM_LOWEND_B_v4": "MGM_LOWEND_B_v4.pth",
+                        "VR Arch Single Model v4: MGM_MAIN_v4": "MGM_MAIN_v4.pth"
+                },
+    
+    "mdx_download_list": {      
+                        "MDX-Net Model: UVR-MDX-NET Inst HQ 1": "UVR-MDX-NET-Inst_HQ_1.onnx",
+                        "MDX-Net Model: UVR-MDX-NET Inst HQ 2": "UVR-MDX-NET-Inst_HQ_2.onnx",
+                        "MDX-Net Model: UVR-MDX-NET Inst HQ 3": "UVR-MDX-NET-Inst_HQ_3.onnx",
+                        "MDX-Net Model: UVR-MDX-NET Inst HQ 4": "UVR-MDX-NET-Inst_HQ_4.onnx",
+                        "MDX-Net Model: UVR-MDX-NET Inst HQ 5": "UVR-MDX-NET-Inst_HQ_5.onnx",
+                        "MDX-Net Model: UVR-MDX-NET Main": "UVR_MDXNET_Main.onnx",
+                        "MDX-Net Model: UVR-MDX-NET Inst Main": "UVR-MDX-NET-Inst_Main.onnx",
+                        "MDX-Net Model: UVR-MDX-NET 1": "UVR_MDXNET_1_9703.onnx",
+                        "MDX-Net Model: UVR-MDX-NET 2": "UVR_MDXNET_2_9682.onnx",
+                        "MDX-Net Model: UVR-MDX-NET 3": "UVR_MDXNET_3_9662.onnx",
+                        "MDX-Net Model: UVR-MDX-NET Inst 1": "UVR-MDX-NET-Inst_1.onnx",
+                        "MDX-Net Model: UVR-MDX-NET Inst 2": "UVR-MDX-NET-Inst_2.onnx",
+                        "MDX-Net Model: UVR-MDX-NET Inst 3": "UVR-MDX-NET-Inst_3.onnx",
+                        "MDX-Net Model: UVR-MDX-NET Karaoke": "UVR_MDXNET_KARA.onnx",
+                        "MDX-Net Model: UVR-MDX-NET Karaoke 2": "UVR_MDXNET_KARA_2.onnx",
+                        "MDX-Net Model: UVR_MDXNET_9482": "UVR_MDXNET_9482.onnx",
+                        "MDX-Net Model: UVR-MDX-NET Voc FT": "UVR-MDX-NET-Voc_FT.onnx",
+                        "MDX-Net Model: Kim Vocal 1": "Kim_Vocal_1.onnx",
+                        "MDX-Net Model: Kim Vocal 2": "Kim_Vocal_2.onnx",
+                        "MDX-Net Model: Kim Inst": "Kim_Inst.onnx",
+                        "MDX-Net Model: Reverb HQ By FoxJoy": "Reverb_HQ_By_FoxJoy.onnx",
+                        "MDX-Net Model: UVR-MDX-NET Crowd HQ 1 By Aufr33": "UVR-MDX-NET_Crowd_HQ_1.onnx",
+                        "MDX-Net Model: kuielab_a_vocals": "kuielab_a_vocals.onnx",
+                        "MDX-Net Model: kuielab_a_other": "kuielab_a_other.onnx",
+                        "MDX-Net Model: kuielab_a_bass": "kuielab_a_bass.onnx",
+                        "MDX-Net Model: kuielab_a_drums": "kuielab_a_drums.onnx",
+                        "MDX-Net Model: kuielab_b_vocals": "kuielab_b_vocals.onnx",
+                        "MDX-Net Model: kuielab_b_other": "kuielab_b_other.onnx",
+                        "MDX-Net Model: kuielab_b_bass": "kuielab_b_bass.onnx",
+                        "MDX-Net Model: kuielab_b_drums": "kuielab_b_drums.onnx"
+                        },
+
+    "demucs_download_list":{
+
+                "Demucs v4: htdemucs_ft":{
+                                "f7e0c4bc-ba3fe64a.th":"https://dl.fbaipublicfiles.com/demucs/hybrid_transformer/f7e0c4bc-ba3fe64a.th",
+                                "d12395a8-e57c48e6.th":"https://dl.fbaipublicfiles.com/demucs/hybrid_transformer/d12395a8-e57c48e6.th",
+                                "92cfc3b6-ef3bcb9c.th":"https://dl.fbaipublicfiles.com/demucs/hybrid_transformer/92cfc3b6-ef3bcb9c.th",
+                                "04573f0d-f3cf25b2.th":"https://dl.fbaipublicfiles.com/demucs/hybrid_transformer/04573f0d-f3cf25b2.th",
+                                "htdemucs_ft.yaml": "https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/htdemucs_ft.yaml"
+                                },
+
+                "Demucs v4: htdemucs":{
+                                "955717e8-8726e21a.th": "https://dl.fbaipublicfiles.com/demucs/hybrid_transformer/955717e8-8726e21a.th",
+                                "htdemucs.yaml": "https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/htdemucs.yaml"
+                                },
+
+                "Demucs v4: hdemucs_mmi":{
+                                "75fc33f5-1941ce65.th": "https://dl.fbaipublicfiles.com/demucs/hybrid_transformer/75fc33f5-1941ce65.th",
+                                "hdemucs_mmi.yaml": "https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/hdemucs_mmi.yaml"
+                                },
+                "Demucs v4: htdemucs_6s":{
+                                "5c90dfd2-34c22ccb.th": "https://dl.fbaipublicfiles.com/demucs/hybrid_transformer/5c90dfd2-34c22ccb.th",
+                                "htdemucs_6s.yaml": "https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/htdemucs_6s.yaml"
+                                },
+                "Demucs v3: mdx":{
+                                "0d19c1c6-0f06f20e.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/0d19c1c6-0f06f20e.th", 
+                                "7ecf8ec1-70f50cc9.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/7ecf8ec1-70f50cc9.th",
+                                "c511e2ab-fe698775.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/c511e2ab-fe698775.th",
+                                "7d865c68-3d5dd56b.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/7d865c68-3d5dd56b.th",
+                                "mdx.yaml": "https://raw.githubusercontent.com/facebookresearch/demucs/main/demucs/remote/mdx.yaml"
+                                },
+                
+                "Demucs v3: mdx_q":{
+                                "6b9c2ca1-3fd82607.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/6b9c2ca1-3fd82607.th",
+                                "b72baf4e-8778635e.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/b72baf4e-8778635e.th",
+                                "42e558d4-196e0e1b.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/42e558d4-196e0e1b.th",
+                                "305bc58f-18378783.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/305bc58f-18378783.th",
+                                "mdx_q.yaml": "https://raw.githubusercontent.com/facebookresearch/demucs/main/demucs/remote/mdx_q.yaml"
+                                },
+                
+                "Demucs v3: mdx_extra":{
+                                "e51eebcc-c1b80bdd.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/e51eebcc-c1b80bdd.th",
+                                "a1d90b5c-ae9d2452.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/a1d90b5c-ae9d2452.th",
+                                "5d2d6c55-db83574e.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/5d2d6c55-db83574e.th",
+                                "cfa93e08-61801ae1.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/cfa93e08-61801ae1.th",
+                                "mdx_extra.yaml": "https://raw.githubusercontent.com/facebookresearch/demucs/main/demucs/remote/mdx_extra.yaml"
+                                },
+                
+                "Demucs v3: mdx_extra_q": {
+                                "83fc094f-4a16d450.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/83fc094f-4a16d450.th",
+                                "464b36d7-e5a9386e.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/464b36d7-e5a9386e.th",
+                                "14fc6a69-a89dd0ee.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/14fc6a69-a89dd0ee.th",
+                                "7fd6ef75-a905dd85.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/7fd6ef75-a905dd85.th",
+                                "mdx_extra_q.yaml": "https://raw.githubusercontent.com/facebookresearch/demucs/main/demucs/remote/mdx_extra_q.yaml"
+                                },
+                
+                "Demucs v3: UVR Model":{
+                                "ebf34a2db.th": "https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/ebf34a2db.th",
+                                "UVR_Demucs_Model_1.yaml": "https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/UVR_Demucs_Model_1.yaml"
+                                },
+
+                "Demucs v3: repro_mdx_a":{
+                                "9a6b4851-03af0aa6.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/9a6b4851-03af0aa6.th", 
+                                "1ef250f1-592467ce.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/1ef250f1-592467ce.th",
+                                "fa0cb7f9-100d8bf4.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/fa0cb7f9-100d8bf4.th",
+                                "902315c2-b39ce9c9.th": "https://dl.fbaipublicfiles.com/demucs/mdx_final/902315c2-b39ce9c9.th",
+                                "repro_mdx_a.yaml": "https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/repro_mdx_a.yaml"
+                                },
+
+                "Demucs v3: repro_mdx_a_time_only":{
+                                "9a6b4851-03af0aa6.th":"https://dl.fbaipublicfiles.com/demucs/mdx_final/9a6b4851-03af0aa6.th",
+                                "1ef250f1-592467ce.th":"https://dl.fbaipublicfiles.com/demucs/mdx_final/1ef250f1-592467ce.th",
+                                "repro_mdx_a_time_only.yaml": "https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/repro_mdx_a_time_only.yaml"
+                                },
+
+                "Demucs v3: repro_mdx_a_hybrid_only":{
+                                "fa0cb7f9-100d8bf4.th":"https://dl.fbaipublicfiles.com/demucs/mdx_final/fa0cb7f9-100d8bf4.th",
+                                "902315c2-b39ce9c9.th":"https://dl.fbaipublicfiles.com/demucs/mdx_final/902315c2-b39ce9c9.th",
+                                "repro_mdx_a_hybrid_only.yaml": "https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/repro_mdx_a_hybrid_only.yaml"
+                                },
+
+                "Demucs v2: demucs": {
+                                "demucs-e07c671f.th": "https://dl.fbaipublicfiles.com/demucs/v3.0/demucs-e07c671f.th"
+                                },
+        
+                "Demucs v2: demucs_extra": {
+                                "demucs_extra-3646af93.th":"https://dl.fbaipublicfiles.com/demucs/v3.0/demucs_extra-3646af93.th"
+                                },
+
+                "Demucs v2: demucs48_hq": {
+                                "demucs48_hq-28a1282c.th":"https://dl.fbaipublicfiles.com/demucs/v3.0/demucs48_hq-28a1282c.th"
+                                },
+
+                "Demucs v2: tasnet": {
+                                "tasnet-beb46fac.th":"https://dl.fbaipublicfiles.com/demucs/v3.0/tasnet-beb46fac.th"
+                                },
+
+                "Demucs v2: tasnet_extra": {
+                                "tasnet_extra-df3777b2.th":"https://dl.fbaipublicfiles.com/demucs/v3.0/tasnet_extra-df3777b2.th"
+                                },
+                                
+                "Demucs v2: demucs_unittest": {
+                                "demucs_unittest-09ebc15f.th":"https://dl.fbaipublicfiles.com/demucs/v3.0/demucs_unittest-09ebc15f.th"
+                                },
+
+                "Demucs v1: demucs": {
+                                "demucs.th":"https://dl.fbaipublicfiles.com/demucs/v2.0/demucs.th"
+                                },
+
+                "Demucs v1: demucs_extra": {
+                                "demucs_extra.th":"https://dl.fbaipublicfiles.com/demucs/v2.0/demucs_extra.th"
+                                },
+
+                "Demucs v1: light": {
+                                "light.th":"https://dl.fbaipublicfiles.com/demucs/v2.0/light.th"
+                                },
+
+                "Demucs v1: light_extra": {
+                                "light_extra.th":"https://dl.fbaipublicfiles.com/demucs/v2.0/light_extra.th"
+                                },
+
+                "Demucs v1: tasnet": {
+                                "tasnet.th":"https://dl.fbaipublicfiles.com/demucs/v2.0/tasnet.th"
+                                },
+                                
+                "Demucs v1: tasnet_extra": {
+                                "tasnet_extra.th":"https://dl.fbaipublicfiles.com/demucs/v2.0/tasnet_extra.th"
+                                }
+                },
+
+    "mdx_download_vip_list": {
+                "MDX-Net Model VIP: UVR-MDX-NET_Main_340": "UVR-MDX-NET_Main_340.onnx",
+                "MDX-Net Model VIP: UVR-MDX-NET_Main_390": "UVR-MDX-NET_Main_390.onnx",
+                "MDX-Net Model VIP: UVR-MDX-NET_Main_406": "UVR-MDX-NET_Main_406.onnx",
+                "MDX-Net Model VIP: UVR-MDX-NET_Main_427": "UVR-MDX-NET_Main_427.onnx",
+                "MDX-Net Model VIP: UVR-MDX-NET_Main_438": "UVR-MDX-NET_Main_438.onnx",
+                "MDX-Net Model VIP: UVR-MDX-NET_Inst_82_beta": "UVR-MDX-NET_Inst_82_beta.onnx",
+                "MDX-Net Model VIP: UVR-MDX-NET_Inst_90_beta": "UVR-MDX-NET_Inst_90_beta.onnx",
+                "MDX-Net Model VIP: UVR-MDX-NET_Inst_187_beta": "UVR-MDX-NET_Inst_187_beta.onnx",
+                "MDX-Net Model VIP: UVR-MDX-NET-Inst_full_292": "UVR-MDX-NET-Inst_full_292.onnx"
+                },
+
+    "mdx23_download_list": {
+                "MDX23C Model: MDX23C_D1581": {"MDX23C_D1581.ckpt":"model_2_stem_061321.yaml"}
+                },
+
+    "mdx23c_download_list": {
+                "MDX23C Model: MDX23C-InstVoc HQ": {"MDX23C-8KFFT-InstVoc_HQ.ckpt":"model_2_stem_full_band_8k.yaml"}
+                },
+    
+    "roformer_download_list": {
+                "Roformer Model: BS-Roformer-Viperx-1297": {"model_bs_roformer_ep_317_sdr_12.9755.ckpt":"model_bs_roformer_ep_317_sdr_12.9755.yaml"},
+                "Roformer Model: BS-Roformer-Viperx-1296": {"model_bs_roformer_ep_368_sdr_12.9628.ckpt":"model_bs_roformer_ep_368_sdr_12.9628.yaml"},
+                "Roformer Model: BS-Roformer-Viperx-1053": {"model_bs_roformer_ep_937_sdr_10.5309.ckpt":"model_bs_roformer_ep_937_sdr_10.5309.yaml"},
+                "Roformer Model: Mel-Roformer-Viperx-1143": {"model_mel_band_roformer_ep_3005_sdr_11.4360.ckpt":"model_mel_band_roformer_ep_3005_sdr_11.4360.yaml"},
+                "Roformer Model: MelBand Roformer Kim | Inst V1 by Unwa": {"melband_roformer_inst_v1.ckpt":"config_melbandroformer_inst.yaml"},
+                "Roformer Model: MelBand Roformer Kim | Inst V2 by Unwa": {"melband_roformer_inst_v2.ckpt":"config_melbandroformer_inst_v2.yaml"},
+                "Roformer Model: MelBand Roformer Kim | InstVoc Duality V1 by Unwa": {"melband_roformer_instvoc_duality_v1.ckpt":"config_melbandroformer_instvoc_duality.yaml"},
+                "Roformer Model: MelBand Roformer Kim | InstVoc Duality V2 by Unwa": {"melband_roformer_instvox_duality_v2.ckpt":"config_melbandroformer_instvoc_duality.yaml"}
+                },
+    
+    "other_network_list": {
+                "Roformer Model: BS-Roformer-Viperx-1297": {"model_bs_roformer_ep_317_sdr_12.9755.ckpt":"https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/model_bs_roformer_ep_317_sdr_12.9755.ckpt",
+                                                            "model_bs_roformer_ep_317_sdr_12.9755.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/model_bs_roformer_ep_317_sdr_12.9755.yaml"},
+                "Roformer Model: BS-Roformer-Viperx-1296": {"model_bs_roformer_ep_368_sdr_12.9628.ckpt":"https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/model_bs_roformer_ep_368_sdr_12.9628.ckpt",
+                                                            "model_bs_roformer_ep_368_sdr_12.9628.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/model_bs_roformer_ep_368_sdr_12.9628.yaml"},
+                "Roformer Model: BS-Roformer-Viperx-1053": {"model_bs_roformer_ep_937_sdr_10.5309.ckpt":"https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/model_bs_roformer_ep_937_sdr_10.5309.ckpt",
+                                                            "model_bs_roformer_ep_937_sdr_10.5309.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/model_bs_roformer_ep_937_sdr_10.5309.yaml"},
+                "Roformer Model: Mel-Roformer-Viperx-1143": {"model_mel_band_roformer_ep_3005_sdr_11.4360.ckpt":"https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/model_mel_band_roformer_ep_3005_sdr_11.4360.ckpt",
+                                                             "model_mel_band_roformer_ep_3005_sdr_11.4360.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/model_mel_band_roformer_ep_3005_sdr_11.4360.yaml"},
+                "Roformer Model: MelBand Roformer Kim | Inst V1 by Unwa": {"melband_roformer_inst_v1.ckpt":"https://huggingface.co/pcunwa/Mel-Band-Roformer-Inst/resolve/main/melband_roformer_inst_v1.ckpt",
+                                                                           "config_melbandroformer_inst.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/config_melbandroformer_inst.yaml"},
+                "Roformer Model: MelBand Roformer Kim | Inst V2 by Unwa": {"melband_roformer_inst_v2.ckpt":"https://huggingface.co/pcunwa/Mel-Band-Roformer-Inst/resolve/main/melband_roformer_inst_v2.ckpt",
+                                                                           "config_melbandroformer_inst_v2.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/config_melbandroformer_inst_v2.yaml"},
+                "Roformer Model: MelBand Roformer Kim | InstVoc Duality V1 by Unwa": {"melband_roformer_instvoc_duality_v1.ckpt":"https://huggingface.co/pcunwa/Mel-Band-Roformer-InstVoc-Duality/resolve/main/melband_roformer_instvoc_duality_v1.ckpt",
+                                                                                      "config_melbandroformer_instvoc_duality.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/config_melbandroformer_instvoc_duality.yaml"},
+                "Roformer Model: MelBand Roformer Kim | InstVoc Duality V2 by Unwa": {"melband_roformer_instvox_duality_v2.ckpt":"https://huggingface.co/pcunwa/Mel-Band-Roformer-InstVoc-Duality/resolve/main/melband_roformer_instvox_duality_v2.ckpt",
+                                                                                      "config_melbandroformer_instvoc_duality.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/config_melbandroformer_instvoc_duality.yaml"},
+                "Roformer Model: MelBand Roformer Kim | Inst V1 (E) by Unwa": {"inst_v1e.ckpt":"https://huggingface.co/pcunwa/Mel-Band-Roformer-Inst/resolve/main/inst_v1e.ckpt",
+                                                                                          "config_melbandroformer_inst.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/config_melbandroformer_inst.yaml"},
+                "Roformer Model: MelBand Roformer Kim": {"MelBandRoformer.ckpt":"https://huggingface.co/KimberleyJSN/melbandroformer/resolve/main/MelBandRoformer.ckpt",
+                                                                                  "config_vocals_mel_band_roformer_kim.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/config_vocals_mel_band_roformer_kim.yaml"}
+                },
+
+    "other_network_list_new": {
+
+        "Roformer Model: BS-Roformer-Inst-EXP-Value-Residual | (by Unwa)": {"BS_Inst_EXP_VRL.ckpt":"https://huggingface.co/pcunwa/BS-Roformer-Inst-EXP-Value-Residual/resolve/main/BS_Inst_EXP_VRL.ckpt",
+                                                                            "BS_Inst_EXP_VRL.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/BS_Inst_EXP_VRL.yaml"},
+        "Roformer Model: Karaoke MelBand Roformer | (by aufr33 & viperx)": {"mel_band_roformer_karaoke_aufr33_viperx_sdr_10.1956.ckpt":"https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/mel_band_roformer_karaoke_aufr33_viperx_sdr_10.1956.ckpt",
+                                                                    "config_mel_band_roformer_karaoke.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/config_mel_band_roformer_karaoke.yaml"},
+        "Roformer Model: BS Roformer Dereverb | (anvuew edition)": {"deverb_bs_roformer_8_256dim_8depth.ckpt":"https://huggingface.co/anvuew/deverb_bs_roformer/resolve/main/deverb_bs_roformer_8_256dim_8depth.ckpt",
+                                                                  "deverb_bs_roformer_8_256dim_8depth.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/deverb_bs_roformer_8_256dim_8depth.yaml"},                                                   
+        "Bandit Plus: Cinematic Bandit Plus | (by kwatcharasupat)": {"model_bandit_plus_dnr_sdr_11.47.ckpt":"https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/model_bandit_plus_dnr_sdr_11.47.ckpt",
+                                                       "config_dnr_bandit_bsrnn_multi_mus64.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/config_dnr_bandit_bsrnn_multi_mus64.yaml"},
+        "Bandit v2: Cinematic Bandit v2 Multilang | (by kwatcharasupat)": {"checkpoint-multi_fixed.ckpt":"https://github.com/TRvlvr/model_repo/releases/download/all_public_uvr_models/checkpoint-multi_fixed.ckpt",
+                                                    "config_dnr_bandit_v2_mus64.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/config_dnr_bandit_v2_mus64.yaml"},
+        "SCnet: 4-stems SCNet_MUSDB18 | (by starrytong)": {"scnet_checkpoint_musdb18.ckpt":"https://github.com/ZFTurbo/Music-Source-Separation-Training/releases/download/v.1.0.6/scnet_checkpoint_musdb18.ckpt",
+                                                           "config_musdb18_scnet.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/config_musdb18_scnet.yaml"},
+        "SCnet: 4-stems SCNet Large | (by starrytong)": {"SCNet-large_starrytong_fixed.ckpt":"https://github.com/ZFTurbo/Music-Source-Separation-Training/releases/download/v1.0.9/SCNet-large_starrytong_fixed.ckpt",
+                                                     "config_musdb18_scnet_large_starrytong.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/config_musdb18_scnet_large_starrytong.yaml"},
+        "SCnet: 4-stems SCNet Large": {"model_scnet_sdr_9.3244.ckpt":"https://github.com/ZFTurbo/Music-Source-Separation-Training/releases/download/v1.0.8/model_scnet_sdr_9.3244.ckpt",
+                                                     "config_musdb18_scnet_large.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/config_musdb18_scnet_large.yaml"},
+        "SCnet: 4-stems SCNet-XL": {"model_scnet_ep_54_sdr_9.8051.ckpt":"https://github.com/ZFTurbo/Music-Source-Separation-Training/releases/download/v1.0.13/model_scnet_ep_54_sdr_9.8051.ckpt",
+                                                     "config_musdb18_scnet_xl.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/config_musdb18_scnet_xl.yaml"},
+        "MDX23C Model: DrumSep 6stem | (by aufr33 & jarredou)": {"aufr33-jarredou_DrumSep_model_mdx23c_ep_141_sdr_10.8059.ckpt":"https://github.com/jarredou/models/releases/download/aufr33-jarredou_MDX23C_DrumSep_model_v0.1/aufr33-jarredou_DrumSep_model_mdx23c_ep_141_sdr_10.8059.ckpt",
+                                                                  "aufr33-jarredou_DrumSep_model_mdx23c_ep_141_sdr_10.8059.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/aufr33-jarredou_DrumSep_model_mdx23c_ep_141_sdr_10.8059.yaml"},
+        "MDX23C Model: Phantom Centre extraction | (by wesleyr36)": {"model_mdx23c_ep_271_l1_freq_72.2383.ckpt":"https://github.com/ZFTurbo/Music-Source-Separation-Training/releases/download/v1.0.10/model_mdx23c_ep_271_l1_freq_72.2383.ckpt",
+                                                                     "config_mdx23c_similarity.yaml":"https://raw.githubusercontent.com/TRvlvr/application_data/main/mdx_model_data/mdx_c_configs/config_mdx23c_similarity.yaml"}
+        },
+
+    "mdx23c_download_vip_list": {
+            "MDX23C Model VIP: MDX23C_D1581": {"MDX23C_D1581.ckpt":"model_2_stem_061321.yaml"},
+            "MDX23C Model VIP: MDX23C-InstVoc HQ 2": {"MDX23C-8KFFT-InstVoc_HQ_2.ckpt":"model_2_stem_full_band_8k.yaml"}
+            },
+
+    "roll_back_win_url": "https://github.com/Anjok07/ultimatevocalremovergui/releases/download/v5.6/UVR_v5.6.0_setup.exe",
+    "roll_back_macos_x86_64_url": "https://github.com/Anjok07/ultimatevocalremovergui/releases/download/v5.6/Ultimate_Vocal_Remover_v5_6_MacOS_x86_64.dmg",
+    "roll_back_macos_arm64_url": "https://github.com/Anjok07/ultimatevocalremovergui/releases/download/v5.6/Ultimate_Vocal_Remover_v5_6_MacOS_arm64.dmg",
+    
+    "vr_download_vip_list": [],
+    "demucs_download_vip_list": []
+}

checkpoints/vocal_separator/mdx_model_data.json

@@ -0,0 +1,482 @@
+{
+    "0ddfc0eb5792638ad5dc27850236c246": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Vocals"
+    },
+    "26d308f91f3423a67dc69a6d12a8793d": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 9,
+        "mdx_n_fft_scale_set": 8192,
+        "primary_stem": "Other"
+    },
+    "2cdd429caac38f0194b133884160f2c6": {
+        "compensate": 1.045,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Instrumental"
+    },
+    "2f5501189a2f6db6349916fabe8c90de": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Vocals",
+        "is_karaoke": true
+    },
+    "398580b6d5d973af3120df54cee6759d": {
+        "compensate": 1.75,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Vocals"
+    },
+    "488b3e6f8bd3717d9d7c428476be2d75": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Instrumental"
+    },
+    "4910e7827f335048bdac11fa967772f9": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 7,
+        "mdx_n_fft_scale_set": 4096,
+        "primary_stem": "Drums"
+    },
+    "53c4baf4d12c3e6c3831bb8f5b532b93": {
+        "compensate": 1.043,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Vocals"
+    },
+    "5d343409ef0df48c7d78cce9f0106781": {
+        "compensate": 1.075,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Vocals"
+    },
+    "5f6483271e1efb9bfb59e4a3e6d4d098": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 9,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Vocals"
+    },
+    "65ab5919372a128e4167f5e01a8fda85": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 8192,
+        "primary_stem": "Other"
+    },
+    "6703e39f36f18aa7855ee1047765621d": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 9,
+        "mdx_n_fft_scale_set": 16384,
+        "primary_stem": "Bass"
+    },
+    "6b31de20e84392859a3d09d43f089515": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Vocals"
+    },
+    "867595e9de46f6ab699008295df62798": {
+        "compensate": 1.03,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Vocals"
+    },
+    "a3cd63058945e777505c01d2507daf37": {
+        "compensate": 1.03,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Vocals"
+    },
+    "b33d9b3950b6cbf5fe90a32608924700": {
+        "compensate": 1.03,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Vocals"
+    },
+    "c3b29bdce8c4fa17ec609e16220330ab": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 16384,
+        "primary_stem": "Bass"
+    },
+    "ceed671467c1f64ebdfac8a2490d0d52": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Instrumental"
+    },
+    "d2a1376f310e4f7fa37fb9b5774eb701": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Instrumental"
+    },
+    "d7bff498db9324db933d913388cba6be": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Vocals"
+    },
+    "d94058f8c7f1fae4164868ae8ae66b20": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Vocals"
+    },
+    "dc41ede5961d50f277eb846db17f5319": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 9,
+        "mdx_n_fft_scale_set": 4096,
+        "primary_stem": "Drums"
+    },
+    "e5572e58abf111f80d8241d2e44e7fa4": {
+        "compensate": 1.028,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Instrumental"
+    },
+    "e7324c873b1f615c35c1967f912db92a": {
+        "compensate": 1.03,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Vocals"
+    },
+    "1c56ec0224f1d559c42fd6fd2a67b154": {
+        "compensate": 1.025,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 5120,
+        "primary_stem": "Instrumental"
+    },
+    "f2df6d6863d8f435436d8b561594ff49": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Instrumental"
+    },
+    "b06327a00d5e5fbc7d96e1781bbdb596": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Instrumental"
+    },
+    "94ff780b977d3ca07c7a343dab2e25dd": {
+        "compensate": 1.039,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Instrumental"
+    },
+    "73492b58195c3b52d34590d5474452f6": {
+        "compensate": 1.043,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Vocals"
+    },
+    "970b3f9492014d18fefeedfe4773cb42": {
+        "compensate": 1.009,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Vocals"
+    },
+    "1d64a6d2c30f709b8c9b4ce1366d96ee": {
+        "compensate": 1.065,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 5120,
+        "primary_stem": "Instrumental",
+        "is_karaoke": true
+    },
+    "203f2a3955221b64df85a41af87cf8f0": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Instrumental"
+    },
+    "291c2049608edb52648b96e27eb80e95": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Instrumental"
+    },
+    "ead8d05dab12ec571d67549b3aab03fc": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Instrumental"
+    },
+    "cc63408db3d80b4d85b0287d1d7c9632": {
+        "compensate": 1.033,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Instrumental"
+    },
+    "cd5b2989ad863f116c855db1dfe24e39": {
+        "compensate": 1.035,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 9,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Reverb"
+    },
+    "55657dd70583b0fedfba5f67df11d711": {
+        "compensate": 1.022,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 6144,
+        "primary_stem": "Instrumental"
+    },
+    "b6bccda408a436db8500083ef3491e8b": {
+        "compensate": 1.02,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Instrumental"
+    },
+    "8a88db95c7fb5dbe6a095ff2ffb428b1": {
+        "compensate": 1.026,
+        "mdx_dim_f_set": 2048,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 5120,
+        "primary_stem": "Instrumental"
+    },
+    "b78da4afc6512f98e4756f5977f5c6b9": {
+        "compensate": 1.021,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Instrumental"
+    },
+    "77d07b2667ddf05b9e3175941b4454a0": {
+        "compensate": 1.021,
+        "mdx_dim_f_set": 3072,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 7680,
+        "primary_stem": "Vocals"
+    },
+    "0f2a6bc5b49d87d64728ee40e23bceb1": {
+        "compensate": 1.019,
+        "mdx_dim_f_set": 2560,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 5120,
+        "primary_stem": "Instrumental"
+    },
+    "cb790d0c913647ced70fc6b38f5bea1a": {
+        "compensate": 1.01,
+        "mdx_dim_f_set": 2560,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 5120,
+        "primary_stem": "Instrumental"
+    },
+    "b02be2d198d4968a121030cf8950b492": {
+        "compensate": 1.02,
+        "mdx_dim_f_set": 2560,
+        "mdx_dim_t_set": 8,
+        "mdx_n_fft_scale_set": 5120,
+        "primary_stem": "No Crowd"
+    },
+    "2154254ee89b2945b97a7efed6e88820": {
+        "config_yaml": "model_2_stem_061321.yaml"
+    },
+    "063aadd735d58150722926dcbf5852a9": {
+        "config_yaml": "model_2_stem_061321.yaml"
+    },
+    "c09f714d978b41d718facfe3427e6001": {
+        "config_yaml": "model_2_stem_061321.yaml"
+    },
+    "fe96801369f6a148df2720f5ced88c19": {
+        "config_yaml": "model3.yaml"
+    },
+    "02e8b226f85fb566e5db894b9931c640": {
+        "config_yaml": "model2.yaml"
+    },
+    "e3de6d861635ab9c1d766149edd680d6": {
+        "config_yaml": "model1.yaml"
+    },
+    "3f2936c554ab73ce2e396d54636bd373": {
+        "config_yaml": "modelB.yaml"
+    },
+    "890d0f6f82d7574bca741a9e8bcb8168": {
+        "config_yaml": "modelB.yaml"
+    },
+    "63a3cb8c37c474681049be4ad1ba8815": {
+        "config_yaml": "modelB.yaml"
+    },
+    "a7fc5d719743c7fd6b61bd2b4d48b9f0": {
+        "config_yaml": "modelA.yaml"
+    },
+    "3567f3dee6e77bf366fcb1c7b8bc3745": {
+        "config_yaml": "modelA.yaml"
+    },
+    "a28f4d717bd0d34cd2ff7a3b0a3d065e": {
+        "config_yaml": "modelA.yaml"
+    },
+    "c9971a18da20911822593dc81caa8be9": {
+        "config_yaml": "sndfx.yaml"
+    },
+    "57d94d5ed705460d21c75a5ac829a605": {
+        "config_yaml": "sndfx.yaml"
+    },
+    "e7a25f8764f25a52c1b96c4946e66ba2": {
+        "config_yaml": "sndfx.yaml"
+    },
+    "104081d24e37217086ce5fde09147ee1": {
+        "config_yaml": "model_2_stem_061321.yaml"
+    },
+    "1e6165b601539f38d0a9330f3facffeb": {
+        "config_yaml": "model_2_stem_061321.yaml"
+    },
+    "fe0108464ce0d8271be5ab810891bd7c": {
+        "config_yaml": "model_2_stem_full_band.yaml"
+    },
+    "e9b82ec90ee56c507a3a982f1555714c": {
+        "config_yaml": "model_2_stem_full_band_2.yaml"
+    },
+    "99b6ceaae542265a3b6d657bf9fde79f": {
+        "config_yaml": "model_2_stem_full_band_8k.yaml"
+    },
+    "116f6f9dabb907b53d847ed9f7a9475f": {
+        "config_yaml": "model_2_stem_full_band_8k.yaml"
+    },
+    "53f707017bfcbb56f5e1bfac420d6732": {
+        "config_yaml": "model_bs_roformer_ep_317_sdr_12.9755.yaml",
+        "is_roformer": true
+    },
+    "63e41acc264bf681a73aa9f7e5f606cc": {
+        "config_yaml": "model_mel_band_roformer_ep_3005_sdr_11.4360.yaml",
+        "is_roformer": true
+    },
+    "e733736763234047587931fc35322fd9": {
+        "config_yaml": "model_bs_roformer_ep_937_sdr_10.5309.yaml",
+        "is_roformer": true
+    },
+    "d7a256bee3e7c620f554bceaab2f68f6": {
+        "config_yaml": "config_melbandroformer_inst.yaml",
+        "is_roformer": true
+    },
+    "365ccfa0e04b31ac2e24bbb935142a81": {
+        "config_yaml": "config_melbandroformer_inst.yaml",
+        "is_roformer": true
+    },
+    "3c15abf122d8eccc4a0eb97bf84a3e58": {
+        "config_yaml": "config_melbandroformer_instvoc_duality.yaml",
+        "is_roformer": true
+    },
+    "9fb197af219c5172ea38703a33aceb79": {
+        "config_yaml": "config_melbandroformer_instvoc_duality.yaml",
+        "is_roformer": true
+    },
+    "d789065adfd747d6f585b27b495bcdae": {
+        "config_yaml": "model_bs_roformer_ep_368_sdr_12.9628.yaml",
+        "is_roformer": true
+    },
+    "e4ca75912fcff3224a19058e55facfbf": {
+        "config_yaml": "config_vocals_mel_band_roformer_kim.yaml",
+        "is_roformer": true
+    },
+    "951f8ef420a941a395a9919f5d55cce9": {
+        "config_yaml": "config_melbandroformer_inst_v2.yaml",
+        "is_roformer": true
+    },
+    "8d306349be961bd1de6b02ee598920b3": {
+        "config_yaml": "config_mel_band_roformer_karaoke.yaml",
+        "is_roformer": true,
+        "model_type": "MelBand-Roformer",
+        "is_karaoke": true
+    },
+    "b1e6014529f71b38dae30aec978c8eb4": {
+        "config_yaml": "aufr33-jarredou_DrumSep_model_mdx23c_ep_141_sdr_10.8059.yaml",
+        "is_roformer": false,
+        "model_type": "MDX23C",
+        "is_karaoke": false
+    },
+    "490993ba65cd8b61a97a7c61650ddb7d": {
+        "config_yaml": "BS_Inst_EXP_VRL.yaml",
+        "is_roformer": true,
+        "model_type": "BS-Roformer v2",
+        "is_karaoke": false
+    },
+    "cfa9cee352938476c31e92656f1b9074": {
+        "config_yaml": "config_dnr_bandit_v2_mus64.yaml",
+        "is_roformer": true,
+        "model_type": "Bandit v2",
+        "is_karaoke": false
+    },
+    "8318a54fe1278ddcf78aad32145c0a6f": {
+        "config_yaml": "deverb_bs_roformer_8_256dim_8depth.yaml",
+        "is_roformer": true,
+        "model_type": "BS-Roformer",
+        "is_karaoke": false
+    },
+    "3bff56e6709357854e71cb2e7802733a": {
+        "config_yaml": "config_dnr_bandit_bsrnn_multi_mus64.yaml",
+        "is_roformer": true,
+        "model_type": "Bandit",
+        "is_karaoke": false
+    },
+    "c7500d7fdb1c0fc24b14b698515462d2": {
+        "config_yaml": "config_mdx23c_similarity.yaml",
+        "is_roformer": false,
+        "model_type": "MDX23C",
+        "is_karaoke": false
+    },
+    "77dd1942c0feb5c04ad0b4effa34fbc6": {
+        "config_yaml": "config_musdb18_scnet_large.yaml",
+        "is_roformer": true,
+        "model_type": "SCNet",
+        "is_karaoke": false
+    },
+    "6e749f5803b8baa7988a10393bb96df1": {
+        "config_yaml": "config_musdb18_scnet.yaml",
+        "is_roformer": true,
+        "model_type": "SCNet",
+        "is_karaoke": false
+    },
+    "bb845b04a3cb0d7a32cdb1f2ce1e007c": {
+        "config_yaml": "config_musdb18_scnet_large_starrytong.yaml",
+        "is_roformer": true,
+        "model_type": "SCNet",
+        "is_karaoke": false
+    },
+    "85b1955d57c0719e94e832eaaeceb0a8": {
+        "config_yaml": "config_musdb18_scnet_xl.yaml",
+        "is_roformer": true,
+        "model_type": "SCNet",
+        "is_karaoke": false
+    }
+    
+}

checkpoints/vocal_separator/vr_model_data.json

@@ -0,0 +1,137 @@
+{
+    "0d0e6d143046b0eecc41a22e60224582": {
+        "vr_model_param": "3band_44100_mid",
+        "primary_stem": "Instrumental"
+    },
+    "18b52f873021a0af556fb4ecd552bb8e": {
+        "vr_model_param": "2band_32000",
+        "primary_stem": "Instrumental"
+    },
+    "1fc66027c82b499c7d8f55f79e64cadc": {
+        "vr_model_param": "2band_32000",
+        "primary_stem": "Instrumental"
+    },
+    "2aa34fbc01f8e6d2bf509726481e7142": {
+        "vr_model_param": "4band_44100",
+        "primary_stem": "No Piano"
+    },
+    "3e18f639b11abea7361db1a4a91c2559": {
+        "vr_model_param": "4band_44100",
+        "primary_stem": "Instrumental"
+    },
+    "570b5f50054609a17741369a35007ddd": {
+        "vr_model_param": "4band_v3",
+        "primary_stem": "Instrumental"
+    },
+    "5a6e24c1b530f2dab045a522ef89b751": {
+        "vr_model_param": "1band_sr44100_hl512",
+        "primary_stem": "Instrumental"
+    },
+    "6b5916069a49be3fe29d4397ecfd73fa": {
+        "vr_model_param": "3band_44100_msb2",
+        "primary_stem": "Instrumental",
+        "is_karaoke": true
+    },
+    "74b3bc5fa2b69f29baf7839b858bc679": {
+        "vr_model_param": "4band_44100",
+        "primary_stem": "Instrumental"
+    },
+    "827213b316df36b52a1f3d04fec89369": {
+        "vr_model_param": "4band_44100",
+        "primary_stem": "Instrumental"
+    },
+    "911d4048eee7223eca4ee0efb7d29256": {
+        "vr_model_param": "4band_44100",
+        "primary_stem": "Vocals"
+    },
+    "941f3f7f0b0341f12087aacdfef644b1": {
+        "vr_model_param": "4band_v2",
+        "primary_stem": "Instrumental"
+    },
+    "a02827cf69d75781a35c0e8a327f3195": {
+        "vr_model_param": "1band_sr33075_hl384",
+        "primary_stem": "Instrumental"
+    },
+    "b165fbff113c959dba5303b74c6484bc": {
+        "vr_model_param": "3band_44100",
+        "primary_stem": "Instrumental"
+    },
+    "b5f988cd3e891dca7253bf5f0f3427c7": {
+        "vr_model_param": "4band_44100",
+        "primary_stem": "Instrumental"
+    },
+    "b99c35723bc35cb11ed14a4780006a80": {
+        "vr_model_param": "1band_sr44100_hl1024",
+        "primary_stem": "Instrumental"
+    },
+    "ba02fd25b71d620eebbdb49e18e4c336": {
+        "vr_model_param": "3band_44100_mid",
+        "primary_stem": "Instrumental"
+    },
+    "c4476ef424d8cba65f38d8d04e8514e2": {
+        "vr_model_param": "3band_44100_msb2",
+        "primary_stem": "Instrumental"
+    },
+    "da2d37b8be2972e550a409bae08335aa": {
+        "vr_model_param": "4band_44100",
+        "primary_stem": "Vocals"
+    },
+    "db57205d3133e39df8e050b435a78c80": {
+        "vr_model_param": "4band_44100",
+        "primary_stem": "Instrumental"
+    },
+    "ea83b08e32ec2303456fe50659035f69": {
+        "vr_model_param": "4band_v3",
+        "primary_stem": "Instrumental"
+    },
+    "f6ea8473ff86017b5ebd586ccacf156b": {
+        "vr_model_param": "4band_v2_sn",
+        "primary_stem": "Instrumental",
+        "is_karaoke": true
+    },
+    "fd297a61eafc9d829033f8b987c39a3d": {
+        "vr_model_param": "1band_sr32000_hl512",
+        "primary_stem": "Instrumental"
+    },
+    "0ec76fd9e65f81d8b4fbd13af4826ed8": {
+        "vr_model_param": "4band_v3",
+        "primary_stem": "No Woodwinds"
+    },
+    "0fb9249ffe4ffc38d7b16243f394c0ff": {
+        "vr_model_param": "4band_v3",
+        "primary_stem": "No Reverb"
+    },
+    "6857b2972e1754913aad0c9a1678c753": {
+        "vr_model_param": "4band_v3",
+        "primary_stem": "No Echo",
+        "nout": 48,
+        "nout_lstm": 128
+    },
+    "f200a145434efc7dcf0cd093f517ed52": {
+        "vr_model_param": "4band_v3",
+        "primary_stem": "No Echo",
+        "nout": 48,
+        "nout_lstm": 128
+    },
+    "44c55d8b5d2e3edea98c2b2bf93071c7": {
+        "vr_model_param": "4band_v3",
+        "primary_stem": "Noise",
+        "nout": 48,
+        "nout_lstm": 128
+    },
+    "51ea8c43a6928ed3c10ef5cb2707d57b": {
+        "vr_model_param": "1band_sr44100_hl1024",
+        "primary_stem": "Noise",
+        "nout": 16,
+        "nout_lstm": 128
+    },
+    "944950a9c5963a5eb70b445d67b7068a": {
+        "vr_model_param": "4band_v3_sn",
+        "primary_stem": "Vocals",
+        "nout": 64,
+        "nout_lstm": 128,
+        "is_karaoke": false,
+        "is_bv_model": true,
+        "is_bv_model_rebalanced": 0.9
+    }
+}

requirements.txt

@@ -1,3 +1,6 @@
+torch==2.6.0 
+torchvision==0.21.0 
+torchaudio==2.6.0
 opencv-python==4.11.0.86
 diffusers==0.34.0
 tokenizers==0.21.4
@@ -22,5 +25,6 @@ audio-separator==0.30.2
 onnxruntime-gpu==1.22.0
 insightface==0.7.3
 transformers==4.52.0
+huggingface_hub
 ninja 
 flash_attn==2.8.1