Upload 4 files

config.json

@@ -0,0 +1,46 @@
+{
+  "train": {
+    "log_interval": 200,
+    "seed": 1234,
+    "epochs": 20000,
+    "learning_rate": 1e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 4,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 12800,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "max_wav_value": 32768.0,
+    "sampling_rate": 40000,
+    "filter_length": 2048,
+    "hop_length": 400,
+    "win_length": 2048,
+    "n_mel_channels": 125,
+    "mel_fmin": 0.0,
+    "mel_fmax": null
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0,
+    "resblock": "1",
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+    "upsample_rates": [10,10,2,2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [16,16,4,4],
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "spk_embed_dim": 109
+  }
+}

cream.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ce2ad107f5dc7dc242a9b78b01dd05f7dda1f1b901bef2fee0e5c3c97544f5
+size 54996633

export_onnx.py

@@ -0,0 +1,85 @@
+from infer_pack.models_onnx_moess import SynthesizerTrnMs256NSFsidM
+from infer_pack.models_onnx import SynthesizerTrnMs256NSFsidO
+import torch
+
+if __name__ == "__main__":
+    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"])
+
+    test_phone = torch.rand(1, 200, hidden_channels)  # hidden unit
+    test_phone_lengths = torch.tensor([200]).long()  # hidden unit 长度（貌似没啥用）
+    test_pitch = torch.randint(size=(1, 200), low=5, high=255)  # 基频（单位赫兹）
+    test_pitchf = torch.rand(1, 200)  # nsf基频
+    test_ds = torch.LongTensor([0])  # 说话人ID
+    test_rnd = torch.rand(1, 192, 200)  # 噪声（加入随机因子）
+
+    device = "cpu"  # 导出时设备（不影响使用模型）
+
+    if MoeVS:
+        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）
+        net_g.load_state_dict(cpt["weight"], strict=False)
+        input_names = ["phone", "phone_lengths", "pitch", "pitchf", "ds", "rnd"]
+        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),
+                test_rnd.to(device),
+            ),
+            ExportedPath,
+            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,
+        )
+    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,
+        )