Docs /Templates/ sinapsis-diarization

SinapsisCanaryASR

sinapsis-diarizationASRasraudiocanarytranscription

Python template · sinapsis_diarization.templates.canary_asr_template

Overview

Canary ASR template. Transcribes an audio using the Canary model: NVIDIA NeMo Canary-Qwen-2.5B is an English speech recognition model that achieves state-of-the art performance on multiple English speech benchmarks. With 2.5 billion parameters and running at 418 RTFx, Canary-Qwen-2.5B supports automatic speech-to-text recognition (ASR) in English with punctuation and capitalization (PnC)

Supported models: 'nvidia/canary-qwen-2.5b'

Attributes: model_name (str): name of model to run 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 root_dir(str): Path to root directory. Optional audio_file_path (str): Path to audio file. Optional

Example agent:

agent: name: my_test_agent templates: - template_name: InputTemplate class_name: InputTemplate attributes: {} - template_name: SinapsisCanaryASR class_name: SinapsisCanaryASR template_input: InputTemplate attributes: model_name: nvidia/canary-qwen-2.5b device: cuda sample_rate: 16000 chunk_size_in_secs: -1 search_window: 5.0 root_dir: null audio_file_path: null

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

device to run the model

typing.Literal['cpu', 'cuda']
Optional
Default: "cuda"
metadata
sinapsis_core.template_base.base_models.TemplateMetadata | None
Optional
Default: null
root_dir

Path to root directory. Optional

str | None
Optional
Default: "/home/ariel/.cache/sinapsis"
model_name

name of model to run

typing.Literal['nvidia/canary-qwen-2.5b']
Optional
Default: "nvidia/canary-qwen-2.5b"
sample_rate

sample rate of the audio

int
Optional
Default: 16000
search_window

Size of the search window

float
Optional
Default: 5
audio_file_path

Path to audio file. Optional

str | None
Optional
Default: null
chunk_size_in_secs

Size of the chunks to divide the audio. -1 for full audio

int
Optional
Default: -1

Configuration example

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

yaml
templates:
  - template_name: "SinapsisCanaryASR"
    class_name: "SinapsisCanaryASR"
    attributes:
      device: "cuda"
      root_dir: "/home/ariel/.cache/sinapsis"
      model_name: "nvidia/canary-qwen-2.5b"
      sample_rate: 16000
      search_window: 5
      audio_file_path: null
      chunk_size_in_secs: -1

Inheritance

Immediate parent: sinapsis_diarization.templates.base_asr_template.SinapsisBaseASR

Environment variables

Environment definitions belong to their canonical Python modules.

No directly related environment variables listed.