jarvissan22/diarization-and-speaker-embedding

Public

525 runs

Run jarvissan22/diarization-and-speaker-embedding 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
file_string	string		Base64 encoded audio file
file_url	string		A direct audio file URL
file	string		An audio file
hf_token	string		Provide a hf.co/settings/token for Pyannote.audio. You need to agree to the terms in 'https://huggingface.co/pyannote/speaker-diarization-3.1' and 'https://huggingface.co/pyannote/segmentation-3.0' first.
num_speakers	integer	Min: 1 Max: 50	Number of speakers, leave empty to autodetect.
min_speakers	integer	1 Min: 1 Max: 50	Minimum number of speakers
max_speakers	integer	10 Min: 1 Max: 50	Maximum number of speakers
language	string	ja	Language of the spoken words as a language code like 'ja'. Leave empty to auto detect language.
batch_size	integer	64 Min: 1	Batch size for inference. (Reduce if face OOM error)
offset_seconds	number	0	Offset in seconds, used for chunked inputs

{
  "type": "object",
  "title": "Input",
  "required": [
    "hf_token"
  ],
  "properties": {
    "file": {
      "type": "string",
      "title": "File",
      "format": "uri",
      "x-order": 2,
      "description": "An audio file"
    },
    "file_url": {
      "type": "string",
      "title": "File Url",
      "x-order": 1,
      "description": "A direct audio file URL"
    },
    "hf_token": {
      "type": "string",
      "title": "Hf Token",
      "x-order": 3,
      "description": "Provide a hf.co/settings/token for Pyannote.audio. You need to agree to the terms in 'https://huggingface.co/pyannote/speaker-diarization-3.1' and 'https://huggingface.co/pyannote/segmentation-3.0' first."
    },
    "language": {
      "type": "string",
      "title": "Language",
      "default": "ja",
      "x-order": 7,
      "description": "Language of the spoken words as a language code like 'ja'. Leave empty to auto detect language."
    },
    "batch_size": {
      "type": "integer",
      "title": "Batch Size",
      "default": 64,
      "minimum": 1,
      "x-order": 8,
      "description": "Batch size for inference. (Reduce if face OOM error)"
    },
    "file_string": {
      "type": "string",
      "title": "File String",
      "x-order": 0,
      "description": "Base64 encoded audio file"
    },
    "max_speakers": {
      "type": "integer",
      "title": "Max Speakers",
      "default": 10,
      "maximum": 50,
      "minimum": 1,
      "x-order": 6,
      "description": "Maximum number of speakers"
    },
    "min_speakers": {
      "type": "integer",
      "title": "Min Speakers",
      "default": 1,
      "maximum": 50,
      "minimum": 1,
      "x-order": 5,
      "description": "Minimum number of speakers"
    },
    "num_speakers": {
      "type": "integer",
      "title": "Num Speakers",
      "maximum": 50,
      "minimum": 1,
      "x-order": 4,
      "description": "Number of speakers, leave empty to autodetect."
    },
    "offset_seconds": {
      "type": "number",
      "title": "Offset Seconds",
      "default": 0,
      "minimum": 0,
      "x-order": 9,
      "description": "Offset in seconds, used for chunked inputs"
    }
  }
}

Output schema

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

Schema

{
  "type": "object",
  "title": "DiarizationEmbeddingOutput",
  "required": [
    "diarization_segments",
    "transcript_segments",
    "speaker_embeddings",
    "speaker_info"
  ],
  "properties": {
    "language": {
      "type": "string",
      "title": "Language"
    },
    "speaker_info": {
      "type": "array",
      "items": {},
      "title": "Speaker Info"
    },
    "speaker_count": {
      "type": "integer",
      "title": "Speaker Count"
    },
    "audio_duration": {
      "type": "number",
      "title": "Audio Duration"
    },
    "processing_time": {
      "type": "number",
      "title": "Processing Time"
    },
    "speaker_embeddings": {
      "type": "object",
      "title": "Speaker Embeddings",
      "additionalProperties": true
    },
    "transcript_segments": {
      "type": "array",
      "items": {},
      "title": "Transcript Segments"
    },
    "diarization_segments": {
      "type": "array",
      "items": {},
      "title": "Diarization Segments"
    }
  }
}