libsvc - 0.0.8 - Native api

优化性能
同时将大部分依赖静态编译

libsvc - 0.0.7 - Native & .Net api

ShallowDiffusion Bug Fix
Infer Pcm Data

libsvc - 0.0.6 - Native & .Net api

Format Code
Bug Fix

libsvc - 0.0.5 - Native & .Net api

Vocoder BUG Fix
Support Write PCM Data

libsvc - 0.0.4 - Native & .Net api

C# example

using LibSvcApi;


LibSvc.LibSvcHparams Config = new();
Config.TensorExtractor = "DiffusionSvc";
Config.SamplingRate = 44100;
Config.HopSize = 512;
Config.HubertPath = "hubert\\vec-768-layer-12.onnx";
Config.SpeakerCount = 2;
Config.HiddenUnitKDims = 768;
Config.EnableCharaMix = 1;
Config.EnableVolume = 1;
Config.MelBins = 128;
Config.DiffusionSvc.After = "Models\\ShallowDiffusion\\ShallowDiffusion_after.onnx";
Config.DiffusionSvc.Alpha = "Models\\ShallowDiffusion\\ShallowDiffusion_alpha.onnx";
Config.DiffusionSvc.Encoder = "Models\\ShallowDiffusion\\ShallowDiffusion_encoder.onnx";
Config.DiffusionSvc.Denoise = "Models\\ShallowDiffusion\\ShallowDiffusion_denoise.onnx";
Config.DiffusionSvc.Naive = "Models\\ShallowDiffusion\\ShallowDiffusion_naive.onnx";
Config.DiffusionSvc.Pred = "Models\\ShallowDiffusion\\ShallowDiffusion_pred.onnx";
void PrintProgress(ulong arg1, ulong arg2)
{
    Console.WriteLine(arg1 * 100.0 / 10);
}

LibSvc.CallbackProgress Callback = new LibSvc.CallbackProgress(PrintProgress);

UnionModel Model = LibSvc.Factory.LoadUnionSvcModel(
    ref Config, ref Callback,
    0, 0, 8
);

string AudioPath = "input.wav";
Int16Vector Audio = LibSvc.Factory.ReadAudio(ref AudioPath, 48000);
Console.WriteLine(Audio.Size());

LibSvc.SlicerSettings slicerSettings = new();
UInt64Vector SlicePos = LibSvc.Factory.SliceAudio(ref Audio, ref slicerSettings);
Console.WriteLine(SlicePos.Size());

Slices slices = LibSvc.Factory.Preprocess(ref Audio, ref SlicePos);
Console.WriteLine(slices.Size());

string VocoderPath = "hifigan\\nsf_hifigan.onnx";
VocoderModel Vocoder = LibSvc.Factory.LoadVocoderModel(ref VocoderPath);

LibSvc.Params _params = new();
_params.SetVocoder(ref Vocoder);
ulong Proc = 0;
Slice slice = slices[0];
Audio = Model.Inference(slice, ref _params, ref Proc);
Console.WriteLine((double)slice.SrcLength() * Config.SamplingRate / slicerSettings.SamplingRate);
Console.WriteLine(Audio.Size());
GC.KeepAlive(Callback);

MoeVoiceStudio - 0.1.3

---

Ver - 0.1.3

UI的变化

• 主要变动
  • 增加了CrashHandler

核心的变化

• 主要变动
  • 支持了ReflowSVC

---

MoeVoiceStudio - 0.1.2

MoeVoiceStudio - 0.1.2
修复了一些BUG

MoeVoiceStudio - TTS - 0.1.4

优化代码结构
修复了几个BUG

MoeVoiceStudio - TTS - 0.1.3

MoeVoiceStudio - TTS - 0.1.3

支持了中文特化和日语特化（其中中文特化需要自行导出Bert的Onnx模型或者等待我导出）

MoeVoiceStudio - 0.1.1

修复了 “Index Out Of Range” 彩蛋始终触发且导致崩溃的BUG

这个彩蛋是为了纪念DiffSvc和SoVits早期 “Index Out Of Range” 的问题