Docs /Templates/ sinapsis-diarization

WhisperxDiarizedTranscription

sinapsis-diarizationASRasraudiodiarizationspeaker_diarization

Python template · sinapsis_diarization.templates.whisperx_asr_diarization_template

Overview

Template that runs an ASR with Diarization pipeline with Whisperx as ASR and Diarization engine

Attributes: root_dir(str): Path to root directory. Optional audio_file_path(str): Path to audio file. Optional asr_model_name (str): Name of the ASR pipeline to use diarization_model_name (str): Name of the diarization pipeline device (str): device to run the model sample_rate (int): sample rate of the audio chunk_size_in_secs (int): Size of the chunks to divide the audio. -1 for full audio search_window (float): Size of the search window diarization_model_name (str): defaults to empty string. Unused in Whisperx pipeline min_speakers (int): minimum speakers to predict max_speakers (int): maximum speakers to predict

Example agent:

agent: name: my_test_agent templates: - template_name: InputTemplate class_name: InputTemplate attributes: {} - template_name: WhisperxDiarizedTranscription class_name: WhisperxDiarizedTranscription template_input: InputTemplate attributes: root_dir: /root/.cache/sinapsis audio_file_path: null asr_model_name: large-v3 diarization_model_name: whisperx device: cuda sample_rate: 16000 chunk_size_in_secs: -1 search_window: 5.0 min_speakers: 1 max_speakers: 2

Capabilities

Capabilities: not set

Installation

Install the published package using pip or uv.

Terminalbash
pip install sinapsis-diarization==1.0.0
uv pip install sinapsis-diarization==1.0.0
uv add sinapsis-diarization==1.0.0

Configuration

Effective fields from the inspector schema, including nested Pydantic model fields.

device
typing.Literal['cpu', 'cuda']
Optional
Default: "cuda"
metadata
sinapsis_core.template_base.base_models.TemplateMetadata | None
Optional
Default: null
root_dir
str | None
Optional
Default: "/home/ariel/.cache/sinapsis"
sample_rate
int
Optional
Default: 16000
max_speakers

maximum speakers to predict

int
Optional
Default: 2
min_speakers

minimum speakers to predict

int
Optional
Default: 1
search_window
float
Optional
Default: 5
asr_model_name
typing.Literal['tiny', 'base', 'small', 'medium', 'large-v1', 'large-v2', 'large-v3']
Optional
Default: "large-v3"
audio_file_path
str | None
Optional
Default: null
chunk_size_in_secs
int
Optional
Default: -1
diarization_model_name

defaults to empty string. Unused in Whisperx pipeline

typing.Literal['whisperx']
Optional
Default: "whisperx"

Configuration example

Generated from documented defaults. Replace any placeholders and complete required nested settings before running.

yaml
templates:
  - template_name: "WhisperxDiarizedTranscription"
    class_name: "WhisperxDiarizedTranscription"
    attributes:
      device: "cuda"
      root_dir: "/home/ariel/.cache/sinapsis"
      sample_rate: 16000
      max_speakers: 2
      min_speakers: 1
      search_window: 5
      asr_model_name: "large-v3"
      audio_file_path: null
      chunk_size_in_secs: -1
      diarization_model_name: "whisperx"

Inheritance

Immediate parent: sinapsis_diarization.templates.asr_diarization_templates.DiarizedTranscriptionBaseTemplate

Environment variables

Environment definitions belong to their canonical Python modules.

No directly related environment variables listed.