Falcon Speaker Diarization
Python API

API Reference for the Python Falcon SDK (PyPI).

pvfalcon.create()

def create(
        access_key: str,
        model_path: Optional[str] = None,
        device: Optional[str] = None,
        library_path: Optional[str] = None) -> Falcon

Factory method for Falcon Speaker Diarization engine.

Parameters

• access_key str : AccessKey obtained from Picovoice Console.
• model_path Optional[str] : Absolute path to the file containing model parameters (.pv).
• device Optional[str] : String representation of the device (e.g., CPU or GPU) to use. If set to best, the most suitable device is selected automatically. If set to gpu, the engine uses the first available GPU device. To select a specific GPU device, set this argument to gpu:${GPU_INDEX}, where ${GPU_INDEX} is the index of the target GPU. If set tocpu, the engine will run on the CPU with the default number of threads. To specify the number of threads, set this argument to cpu:${NUM_THREADS}, where ${NUM_THREADS} is the desired number of threads.
• library_path Optional[str] : Absolute path to Falcon's dynamic library.

Returns

• Falcon : An instance of Falcon Speaker Diarization engine.

Throws

• FalconError

pvfalcon.available_devices()

def available_devices(library_path: Optional[str] = None) -> Sequence[str]

Lists all available devices that Falcon can use for inference. Each entry in the list can be the device argument of create() factory method or Falcon constructor.

Parameters

• library_path Optional[str] : Absolute path to Falcon's dynamic library. If not set it will be set to the default location.

Returns

• Sequence[str]: List of all available devices that Falcon can use for inference.

Throws

• FalconError

pvfalcon.Falcon

class Falcon(object)

Class for the Falcon Speaker Diarization engine. Falcon can be initialized either using the module level create() function or directly using the class __init__() method. Resources should be cleaned when you are done using the delete() method.

pvfalcon.Falcon.version

self.version: str

The version string of the Falcon library.

pvfalcon.Falcon.sample_rate

self.sample_rate: int

The audio sample rate the Falcon accepts.

pvfalcon.Falcon.__init__()

def __init__(
        self,
        access_key: str,
        model_path: str,
        device: str,
        library_path: str) -> Falcon

__init__ method for Falcon Speaker Diarization engine.

Parameters

• access_key str : AccessKey obtained from Picovoice Console.
• model_path str : Absolute path to the file containing model parameters (.pv).
• device str : String representation of the device (e.g., CPU or GPU) to use. If set to best, the most suitable device is selected automatically. If set to gpu, the engine uses the first available GPU device. To select a specific GPU device, set this argument to gpu:${GPU_INDEX}, where ${GPU_INDEX} is the index of the target GPU. If set tocpu, the engine will run on the CPU with the default number of threads. To specify the number of threads, set this argument to cpu:${NUM_THREADS}, where ${NUM_THREADS} is the desired number of threads.
• library_path str : Absolute path to Falcon's dynamic library.

Returns

• Falcon: An instance of Falcon Speaker Diarization engine.

Throws

• FalconError

pvfalcon.Falcon.delete()

def delete(self)

Releases resources acquired by Falcon.

pvfalcon.Falcon.process()

def process(self, pcm: Sequence[int]) -> Sequence[Segment]

Processes the given audio data and returns the diarization output. The audio needs to have a sample rate equal to .sample_rate and be 16-bit linearly-encoded. This function operates on single-channel audio. If you wish to process data in a different sample rate or format consider using .process_file().

Parameters

• pcm Sequence[int] : Audio data.

Returns

• Sequence[Segment] : Diarization output as a sequence of segments. Each segment is a tuple of (start_sec, end_sec, speaker_tag).

Throws

• FalconError

pvfalcon.Falcon.process_file()

def process_file(self, audio_path: str) -> Sequence[Segment]

Processes a given audio file and returns the diarization output. The supported audio formats are: 3gp (AMR), FLAC, MP3, MP4/m4a (AAC), Ogg, WAV, and WebM.

Parameters

• audio_path str : Absolute path to the audio file.

Returns

• Sequence[Segment] : Diarization output as a sequence of segments. Each segment is a tuple of (start_sec, end_sec, speaker_tag).

Throws

• FalconError

pvfalcon.list_hardware_devices()

def list_hardware_devices(library_path: str) -> Sequence[str]:

Lists all available devices that Falcon can use for inference. Each entry in the list can be the device argument of create() factory method or Falcon constructor.

Internal method. The higher level pvfalcon.available_devices() should be used instead.

Parameters

• library_path str : Absolute path to Falcon's dynamic library.

Returns

• Sequence[str]: List of all available devices that Falcon can use for inference.

Throws

• FalconError

pvfalcon.Falcon.Segment

Segment = namedtuple('Segment', ['start_sec', 'end_sec', 'speaker_tag'])

Named tuple for representing a speaker diarization segment.

• start_sec float : Start time of the segment in seconds.
• end_sec float : End time of the segment in seconds.
• speaker_tag int : Speaker tag identifier - a non-negative integer that uniquely identifies a speaker.

pvfalcon.FalconError

class FalconError(Exception)

Error thrown if an error occurs within Falcon Speaker Diarization engine.

Exceptions

class FalconActivationError(FalconError)
class FalconActivationLimitError(FalconError)
class FalconActivationRefusedError(FalconError)
class FalconActivationThrottledError(FalconError)
class FalconIOError(FalconError)
class FalconInvalidArgumentError(FalconError)
class FalconInvalidStateError(FalconError)
class FalconKeyError(FalconError)
class FalconMemoryError(FalconError)
class FalconRuntimeError(FalconError)
class FalconStopIterationError(FalconError)