PyTorch Extension

Extension No Longer Available

The PyTorch Extension is no longer available from Switchboard. If you need PyTorch-based ML audio processing, get in touch at hello@synervoz.com.

PyTorch is a widely used open-source deep learning framework known for its dynamic and intuitive programming interface. It provides a versatile platform for developing machine learning models, including those used in audio processing. PyTorch is well-suited for various audio processing use-cases such as speech recognition, music analysis, sound classification, audio synthesis, and voice conversion.

The PyTorch Extension provided the following audio nodes for a Switchboard SDK audio graph:

Node	Description
PyTorchSourceNode	A source node that runs the PyTorch model and generates audio data with the specified post-processing. Ideal for use with generative audio use cases.
PyTorchSinkNode	A sink node that runs the PyTorch model and receives audio data with the specified pre-processing. Ideal to be used for classifier type models.
PyTorchProcessorNode	A processor node that runs the PyTorch model and receives audio data with the specified pre-processing, then generates audio data with the specified post-processing. Ideal for applications in audio transformation, such as Noise Reduction, Source Separation, and Voice Conversion.