> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/curator/v26.04/nemo-curator/nemo_curator/models/audio/sed/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/curator/_mcp/server.

# nemo_curator.models.audio.sed

Sound-event-detection model architectures and lazy PANNs registry.

Resolution is lazy so importing the SED stage does not require
`torchlibrosa` until a model is built.

## Submodules

* **[`nemo_curator.models.audio.sed.base`](/nemo/curator/nemo-curator/nemo_curator/models/audio/sed/base)**
* **[`nemo_curator.models.audio.sed.build_sed_tensorrt_engine`](/nemo/curator/nemo-curator/nemo_curator/models/audio/sed/build_sed_tensorrt_engine)**
* **[`nemo_curator.models.audio.sed.cnn14`](/nemo/curator/nemo-curator/nemo_curator/models/audio/sed/cnn14)**
* **[`nemo_curator.models.audio.sed.panns`](/nemo/curator/nemo-curator/nemo_curator/models/audio/sed/panns)**
* **[`nemo_curator.models.audio.sed.tensorrt`](/nemo/curator/nemo-curator/nemo_curator/models/audio/sed/tensorrt)**

## Package Contents

### Functions

| Name                                                                | Description                                                   |
| ------------------------------------------------------------------- | ------------------------------------------------------------- |
| [`get_model_class`](#nemo_curator-models-audio-sed-get_model_class) | Resolve a checkpoint name to its vendored architecture class. |

### Data

[`SUPPORTED_MODEL_TYPES`](#nemo_curator-models-audio-sed-SUPPORTED_MODEL_TYPES)

[`_MODEL_CLASS_NAMES`](#nemo_curator-models-audio-sed-_MODEL_CLASS_NAMES)

### API

```python
nemo_curator.models.audio.sed.get_model_class(
    model_type: str
) -> type[torch.nn.Module]
```

Resolve a checkpoint name to its vendored architecture class.

```python
nemo_curator.models.audio.sed.SUPPORTED_MODEL_TYPES: tuple[str, ...] = tuple(_MODEL_CLASS_NAMES)
```

```python
nemo_curator.models.audio.sed._MODEL_CLASS_NAMES: dict[str, str] = {'Cnn14_DecisionLevelMax': 'Cnn14DecisionLevelMax', 'Cnn14_DecisionLevelAvg': 'C...
```

## Docs

- [nemo_curator.models.audio.sed.base](https://docs.nvidia.com/nemo/curator/v26.04/nemo-curator/nemo_curator/models/audio/sed/base.md)
- [nemo_curator.models.audio.sed.build_sed_tensorrt_engine](https://docs.nvidia.com/nemo/curator/v26.04/nemo-curator/nemo_curator/models/audio/sed/build_sed_tensorrt_engine.md)
- [nemo_curator.models.audio.sed.cnn14](https://docs.nvidia.com/nemo/curator/v26.04/nemo-curator/nemo_curator/models/audio/sed/cnn14.md)
- [nemo_curator.models.audio.sed.panns](https://docs.nvidia.com/nemo/curator/v26.04/nemo-curator/nemo_curator/models/audio/sed/panns.md)
- [nemo_curator.models.audio.sed.tensorrt](https://docs.nvidia.com/nemo/curator/v26.04/nemo-curator/nemo_curator/models/audio/sed/tensorrt.md)