<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/python/audio/audio_transcriber.py#L176-L196) |

Options for MediaPipe AudioTranscriber task.

    mp.tasks.audio.AudioTranscriberOptions(
        base_options: https://developers.google.com/edge/api/mediapipe/python/mp/tasks/BaseOptions,
        sample_rate_hz: int = 16000,
        enable_interim_results: bool = False,
        model_architecture: https://developers.google.com/edge/api/mediapipe/python/mp/tasks/audio/ModelArchitecture = ModelArchitecture.AUTO,
        prompt: Optional[str] = None,
        cache_dir: Optional[str] = None
    )

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `base_options` | Base options for the MediaPipe task (model path and delegate). |
| `sample_rate_hz` | Input PCM audio sample rate in Hz. |
| `enable_interim_results` | Whether to emit interim hypotheses during streaming. |
| `model_architecture` | ASR model family routing (`AUTO`, `OMNI`, or `TINY_GEMMA`). |
| `prompt` | Optional decoding prompt override; `None` uses the model default. |
| `cache_dir` | Optional directory path for compiled weight/program caches; `None` disables disk caching. |

<br />

## Methods

### `__eq__`

    __eq__(
        other
    )

Return self==value.

<br />

<br />

<br />

| ## Class Variables ||
|---|---|
| cache_dir | `None` |
| enable_interim_results | `False` |
| model_architecture | `<ModelArchitecture.AUTO: 0>` |
| prompt | `None` |
| sample_rate_hz | `16000` |

<br />