openvino_genai.ASRPipeline#

class openvino_genai.ASRPipeline#

Bases: pybind11_object

Automatic speech recognition pipeline

__init__(self: openvino_genai.py_openvino_genai.ASRPipeline, models_path: os.PathLike | str | bytes, device: str, **kwargs) → None#

ASRPipeline class constructor. models_path (os.PathLike): Path to the model file. device (str): Device to run the model on (e.g., CPU, GPU).

Methods

__delattr__(name, /)

Implement delattr(self, name).

__dir__()

Default dir() implementation.

__eq__(value, /)

Return self==value.

__format__(format_spec, /)

Default object formatter.

__ge__(value, /)

Return self>=value.

__getattribute__(name, /)

Return getattr(self, name).

__getstate__()

Helper for pickle.

__gt__(value, /)

Return self>value.

__hash__()

Return hash(self).

__init__(self, models_path, device, **kwargs)

ASRPipeline class constructor.

__init_subclass__

This method is called when a class is subclassed.

__le__(value, /)

Return self<=value.

__lt__(value, /)

Return self<value.

__ne__(value, /)

Return self!=value.

__new__(**kwargs)

__reduce__()

Helper for pickle.

__reduce_ex__(protocol, /)

Helper for pickle.

__repr__()

Return repr(self).

__setattr__(name, value, /)

Implement setattr(self, name, value).

__sizeof__()

Size of object in memory, in bytes.

__str__()

Return str(self).

__subclasshook__

Abstract classes can override this to customize issubclass().

_pybind11_conduit_v1_

generate(self, audio_inputs[, ...])

High level generate that receives raw speech as a vector of floats and returns decoded output.

get_generation_config(self)

get_tokenizer(self)

set_generation_config(self, config)

Attributes

__annotations__

__annotations__ = {}#
__class__#

alias of pybind11_type

__delattr__(name, /)#

Implement delattr(self, name).

__dir__()#

Default dir() implementation.

__eq__(value, /)#

Return self==value.

__format__(format_spec, /)#

Default object formatter.

Return str(self) if format_spec is empty. Raise TypeError otherwise.

__ge__(value, /)#

Return self>=value.

__getattribute__(name, /)#

Return getattr(self, name).

__getstate__()#

Helper for pickle.

__gt__(value, /)#

Return self>value.

__hash__()#

Return hash(self).

__init__(self: openvino_genai.py_openvino_genai.ASRPipeline, models_path: os.PathLike | str | bytes, device: str, **kwargs) → None#

ASRPipeline class constructor. models_path (os.PathLike): Path to the model file. device (str): Device to run the model on (e.g., CPU, GPU).

__init_subclass__()#

This method is called when a class is subclassed.

The default implementation does nothing. It may be overridden to extend subclasses.

__le__(value, /)#

Return self<=value.

__lt__(value, /)#

Return self<value.

__ne__(value, /)#

Return self!=value.

__new__(**kwargs)#
__reduce__()#

Helper for pickle.

__reduce_ex__(protocol, /)#

Helper for pickle.

__repr__()#

Return repr(self).

__setattr__(name, value, /)#

Implement setattr(self, name, value).

__sizeof__()#

Size of object in memory, in bytes.

__str__()#

Return str(self).

__subclasshook__()#

Abstract classes can override this to customize issubclass().

This is invoked early on by abc.ABCMeta.__subclasscheck__(). It should return True, False or NotImplemented. If it returns NotImplemented, the normal algorithm is used. Otherwise, it overrides the normal algorithm (and the outcome is cached).

_pybind11_conduit_v1_()#
generate(self: openvino_genai.py_openvino_genai.ASRPipeline, audio_inputs: collections.abc.Sequence[SupportsFloat], generation_config: openvino_genai.py_openvino_genai.ASRGenerationConfig | None = None, streamer: collections.abc.Callable[[str], int | None] | openvino_genai.py_openvino_genai.StreamerBase | None = None, **kwargs) → openvino_genai.py_openvino_genai.ASRDecodedResults#

High level generate that receives raw speech as a vector of floats and returns decoded output.

Parameters:

  • audio_inputs (list[float]) – inputs in the form of list of floats. Required to be normalized to near [-1, 1] range and have 16k Hz sampling rate.

  • generation_config (ASRGenerationConfig) – generation_config

  • streamer – streamer either as a lambda with a boolean returning flag whether generation should be stopped. Streamer supported for short-form audio (< 30 seconds) with return_timestamps=False only

:type : Callable[[str], bool], ov.genai.StreamerBase

Parameters:

kwargs – arbitrary keyword arguments with keys corresponding to ASRGenerationConfig fields.

:type : dict

Returns:

return results in decoded form

Return type:

ASRDecodedResults

ASRGenerationConfig

Common parameters:

Parameters:

  • language (Optional[str]) – Language token to use for generation. In the form of <|en|> for Whisper models. Can be set for multilingual models only. In the form of English for Qwen3-ASR models.

  • return_timestamps (bool) – Whether to return segment-level timestamps.

Whisper parameters:

Parameters:

  • decoder_start_token_id (int) – Corresponds to the “<|startoftranscript|>” token.

  • pad_token_id (int) – Padding token id.

  • translate_token_id (int) – Translate token id.

  • transcribe_token_id (int) – Transcribe token id.

  • prev_sot_token_id (int) – Corresponds to the “<|startofprev|>” token.

  • no_timestamps_token_id (int) – No timestamps token id.

  • begin_suppress_tokens (list[int]) – A list containing tokens that will be suppressed at the beginning of the sampling process.

  • suppress_tokens (list[int]) – A list containing the non-speech tokens that will be suppressed during generation.

  • max_initial_timestamp_index (int) – Maximum initial timestamp index.

  • is_multilingual (bool) – Whether the model is multilingual.

  • task (Optional[str]) – Task to use for generation, either “translate” or “transcribe”. Can be set for multilingual models only.

  • lang_to_id (dict[str, int]) – Language token to token_id map. Initialized from the generation_config.json lang_to_id dictionary.

  • word_timestamps (bool) – If true the pipeline will return word-level timestamps. When enabled word_timestamps=True property should be passed to ASRPipeline constructor: ASRPipeline(“model_path”, “CPU”, word_timestamps=True)

  • alignment_heads (list[tuple[int, int]]) – Encoder attention alignment heads used for word-level timestamps prediction. Each pair represents (layer_index, head_index).

  • initial_prompt (Optional[str]) –

    Initial prompt tokens passed as a previous transcription (after <|startofprev|> token) to the first processing window. Can be used to steer the model to use particular spellings or styles.

    Example:

    result = pipeline.generate(raw_speech)
#  He has gone and gone for good answered Paul Icrom who...

result = pipeline.generate(raw_speech, initial_prompt="Polychrome")
#  He has gone and gone for good answered Polychrome who...

  • hotwords (Optional[str]) –

    Hotwords tokens passed as a previous transcription (after <|startofprev|> token) to all processing windows. Can be used to steer the model to use particular spellings or styles.

    Example:

    result = pipeline.generate(raw_speech)
#  He has gone and gone for good answered Paul Icrom who...

result = pipeline.generate(raw_speech, hotwords="Polychrome")
#  He has gone and gone for good answered Polychrome who...

Qwen3-ASR parameters:

Parameters:

context (Optional[str]) – System prompt context prepended to Qwen3-ASR transcription requests.

For generic generation parameters (max_length, max_new_tokens, num_beams, temperature, etc.) see GenerationConfig documentation.

get_generation_config(self: openvino_genai.py_openvino_genai.ASRPipeline) → openvino_genai.py_openvino_genai.ASRGenerationConfig#
get_tokenizer(self: openvino_genai.py_openvino_genai.ASRPipeline) → openvino_genai.py_openvino_genai.Tokenizer#
set_generation_config(self: openvino_genai.py_openvino_genai.ASRPipeline, config: openvino_genai.py_openvino_genai.ASRGenerationConfig) → None#