NeuralCodecs is a .NET library for neural audio codec implementations, designed for efficient audio compression and reconstruction.
- DAC: Descript Audio Codec
- Torchsharp or libTorch targeting your desired platform
There are several ways to load a model:
- Using static factory method:
// Load SNAC model with static method provided for built-in models
var model = await NeuralCodecs.CreateSNACAsync("model.pt");
- SnacConfig provides premade configurations for 24kHz, 32kHz, and 44kHz sampling rates.
var model = await NeuralCodecs.CreateSNACAsync(modelPath, SNACConfig.SNAC24Khz);
- Allows the use of custom loader implementations
// Load model with default config from IModelLoader instance
var torchLoader = NeuralCodecs.CreateTorchLoader();
var model = await torchLoader.LoadModelAsync<SNAC, SNACConfig>("model.pt");
var config = new SNACConfig { /* ... */ };
var model = await torchLoader.LoadModelAsync<SNAC, SNACConfig>("model.pt", config);
- Allows the use of custom model implementations with built-in loaders
// Load custom model with factory method
var model = await torchLoader.LoadModelAsync<CustomModel, CustomConfig>(
"model.pt",
config => new CustomModel(config, ...),
config);
There are two main ways to process audio:
- Using the simplified ProcessAudio method:
// Compress audio in one step
var processedAudio = model.ProcessAudio(audioData, sampleRate);
- Using separate encode and decode steps:
// Encode audio to compressed format
var codes = model.Encode(buffer);
// Decode back to audio
var processedAudio = model.Decode(codes);
-
Saving the processed audio
Use your preferred method to save WAV files
// using NAudio
await using var writer = new WaveFileWriter(
outputPath,
new WaveFormat(model.Config.SamplingRate, 1)
);
writer.WriteSamples(processedAudio, 0, processedAudio.Length);
- SNAC - Original SNAC implementation
- Descript Audio Codec - DAC reference
Suggestions and contributions are welcome! Feel free to submit a pull request.
This project is licensed under the MIT License.
