Add files via upload

export_onnx.py

@@ -1,47 +1,81 @@
-from infer_pack.models_onnx import SynthesizerTrnMs256NSFsid
+from infer_pack.models_onnx_moess import SynthesizerTrnMs256NSFsidM
+from infer_pack.models_onnx import SynthesizerTrnMs256NSFsidO
 import torch
 
-person = "Shiroha/shiroha.pth"
+if __name__ == '__main__':
-exported_path = "model.onnx"
+    MoeVS = True #模型是否为MoeVoiceStudio（原MoeSS）使用
 
+    ModelPath = "Shiroha/shiroha.pth"  #模型路径
+    ExportedPath = "model.onnx"        #输出路径
+    hidden_channels = 256                                              # hidden_channels，为768Vec做准备
+    cpt = torch.load(ModelPath, map_location="cpu")                   
+    cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0]         # n_spk
+    print(*cpt["config"])
 
-cpt = torch.load(person, map_location="cpu")
+    test_phone = torch.rand(1, 200, hidden_channels)                   # hidden unit
-cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0]  # n_spk
+    test_phone_lengths = torch.tensor([200]).long()                    # hidden unit 长度（貌似没啥用）
-print(*cpt["config"])
+    test_pitch = torch.randint(size=(1, 200), low=5, high=255)         # 基频（单位赫兹）
-net_g = SynthesizerTrnMs256NSFsid(*cpt["config"], is_half=False)
+    test_pitchf = torch.rand(1, 200)                                   # nsf基频
-net_g.load_state_dict(cpt["weight"], strict=False)
+    test_ds = torch.LongTensor([0])                                    # 说话人ID
+    test_rnd = torch.rand(1, 192, 200)                                 # 噪声（加入随机因子）
 
-test_phone = torch.rand(1, 200, 256)
+    device = "cpu"  #导出时设备（不影响使用模型）
-test_phone_lengths = torch.tensor([200]).long()
+
-test_pitch = torch.randint(size=(1, 200), low=5, high=255)
+    if MoeVS:
-test_pitchf = torch.rand(1, 200)
+        net_g = SynthesizerTrnMs256NSFsidM(*cpt["config"], is_half=False)   # fp32导出（C++要支持fp16必须手动将内存重新排列所以暂时不用fp16）
-test_ds = torch.LongTensor([0])
+        net_g.load_state_dict(cpt["weight"], strict=False)
-test_rnd = torch.rand(1, 192, 200)
+        input_names = ["phone", "phone_lengths", "pitch", "pitchf", "ds", "rnd"]
-input_names = ["phone", "phone_lengths", "pitch", "pitchf", "ds", "rnd"]
+        output_names = [
-output_names = [
+            "audio",
-    "audio",
+        ]
-]
+        torch.onnx.export(
-device = "cpu"
+            net_g,
-torch.onnx.export(
+            (
-    net_g,
+                test_phone.to(device),
-    (
+                test_phone_lengths.to(device),
-        test_phone.to(device),
+                test_pitch.to(device),
-        test_phone_lengths.to(device),
+                test_pitchf.to(device),
-        test_pitch.to(device),
+                test_ds.to(device),
-        test_pitchf.to(device),
+                test_rnd.to(device),
-        test_ds.to(device),
+            ),
-        test_rnd.to(device),
+            ExportedPath,
-    ),
+            dynamic_axes={
-    exported_path,
+                "phone": [1],
-    dynamic_axes={
+                "pitch": [1],
-        "phone": [1],
+                "pitchf": [1],
-        "pitch": [1],
+                "rnd": [2],
-        "pitchf": [1],
+            },
-        "rnd": [2],
+            do_constant_folding=False,
-    },
+            opset_version=16,
-    do_constant_folding=False,
+            verbose=False,
-    opset_version=16,
+            input_names=input_names,
-    verbose=False,
+            output_names=output_names,
-    input_names=input_names,
+        )
-    output_names=output_names,
+    else:
-)
+        net_g = SynthesizerTrnMs256NSFsidO(*cpt["config"], is_half=False)   # fp32导出（C++要支持fp16必须手动将内存重新排列所以暂时不用fp16）
+        net_g.load_state_dict(cpt["weight"], strict=False)
+        input_names = ["phone", "phone_lengths", "pitch", "pitchf", "ds"]
+        output_names = [
+            "audio",
+        ]
+        torch.onnx.export(
+            net_g,
+            (
+                test_phone.to(device),
+                test_phone_lengths.to(device),
+                test_pitch.to(device),
+                test_pitchf.to(device),
+                test_ds.to(device),
+            ),
+            ExportedPath,
+            dynamic_axes={
+                "phone": [1],
+                "pitch": [1],
+                "pitchf": [1],
+            },
+            do_constant_folding=False,
+            opset_version=16,
+            verbose=False,
+            input_names=input_names,
+            output_names=output_names,
+        )

export_onnx_old.py

@@ -0,0 +1,47 @@
+from infer_pack.models_onnx_moess import SynthesizerTrnMs256NSFsidM
+import torch
+
+person = "Shiroha/shiroha.pth"
+exported_path = "model.onnx"
+
+
+cpt = torch.load(person, map_location="cpu")
+cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0]  # n_spk
+print(*cpt["config"])
+net_g = SynthesizerTrnMs256NSFsidM(*cpt["config"], is_half=False)
+net_g.load_state_dict(cpt["weight"], strict=False)
+
+test_phone = torch.rand(1, 200, 256)
+test_phone_lengths = torch.tensor([200]).long()
+test_pitch = torch.randint(size=(1, 200), low=5, high=255)
+test_pitchf = torch.rand(1, 200)
+test_ds = torch.LongTensor([0])
+test_rnd = torch.rand(1, 192, 200)
+input_names = ["phone", "phone_lengths", "pitch", "pitchf", "ds", "rnd"]
+output_names = [
+    "audio",
+]
+device = "cpu"
+torch.onnx.export(
+    net_g,
+    (
+        test_phone.to(device),
+        test_phone_lengths.to(device),
+        test_pitch.to(device),
+        test_pitchf.to(device),
+        test_ds.to(device),
+        test_rnd.to(device),
+    ),
+    exported_path,
+    dynamic_axes={
+        "phone": [1],
+        "pitch": [1],
+        "pitchf": [1],
+        "rnd": [2],
+    },
+    do_constant_folding=False,
+    opset_version=16,
+    verbose=False,
+    input_names=input_names,
+    output_names=output_names,
+)