turian/audio-super-resolution-improved

turian / audio-super-resolution-improved

Public
58 runs

Run turian/audio-super-resolution-improved with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
input_file	string		Audio to upsample
model	string (enum)	basic Options: basic, speech	Checkpoint (basic or speech)
ddim_steps	integer	50 Min: 10 Max: 500	Number of inference steps
guidance_scale	number	3.5 Min: 1 Max: 20	Scale for classifier free guidance
overlap	number	0.75	Window overlap, higher will give better predictions, between 0 and 1
seed	integer		Random seed. Leave blank to randomize the seed
output_bitrate	integer (enum)	32 Options: 32, 16	WAV output bitrate

{
  "type": "object",
  "title": "Input",
  "required": [
    "input_file"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "x-order": 5,
      "description": "Random seed. Leave blank to randomize the seed"
    },
    "model": {
      "enum": [
        "basic",
        "speech"
      ],
      "type": "string",
      "title": "model",
      "description": "Checkpoint (basic or speech)",
      "default": "basic",
      "x-order": 1
    },
    "overlap": {
      "type": "number",
      "title": "Overlap",
      "default": 0.75,
      "x-order": 4,
      "description": "Window overlap, higher will give better predictions, between 0 and 1"
    },
    "ddim_steps": {
      "type": "integer",
      "title": "Ddim Steps",
      "default": 50,
      "maximum": 500,
      "minimum": 10,
      "x-order": 2,
      "description": "Number of inference steps"
    },
    "input_file": {
      "type": "string",
      "title": "Input File",
      "format": "uri",
      "x-order": 0,
      "description": "Audio to upsample"
    },
    "guidance_scale": {
      "type": "number",
      "title": "Guidance Scale",
      "default": 3.5,
      "maximum": 20,
      "minimum": 1,
      "x-order": 3,
      "description": "Scale for classifier free guidance"
    },
    "output_bitrate": {
      "enum": [
        32,
        16
      ],
      "type": "integer",
      "title": "output_bitrate",
      "description": "WAV output bitrate",
      "default": 32,
      "x-order": 6
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}