openvino_genai.ASRGenerationConfig#

class openvino_genai.ASRGenerationConfig#

Bases: GenerationConfig

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.

__init__(*args, **kwargs)#

Overloaded function.

__init__(self: openvino_genai.py_openvino_genai.ASRGenerationConfig, json_path: os.PathLike | str | bytes) -> None

path where generation_config.json is stored

__init__(self: openvino_genai.py_openvino_genai.ASRGenerationConfig, **kwargs) -> None

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__`(args, *kwargs)	Overloaded function.
`__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_`
`is_assisting_generation`(self)
`is_beam_search`(self)
`is_greedy_decoding`(self)
`is_multinomial`(self)
`is_prompt_lookup`(self)
`is_tree_search`(self)
`set_eos_token_id`(self, tokenizer_eos_token_id)
`update_generation_config`(self, **kwargs)
`validate`(self)

Attributes

`__annotations__`
`adapters`
`alignment_heads`
`apply_chat_template`
`assistant_confidence_threshold`
`begin_suppress_tokens`
`branching_factor`	Number of branches (top-k) at each level of the candidate tree
`context`
`decoder_start_token_id`
`diversity_penalty`
`do_sample`
`echo`
`eos_token_id`
`frequency_penalty`
`hotwords`
`ignore_eos`
`include_stop_str_in_output`
`initial_prompt`
`is_multilingual`
`lang_to_id`
`language`
`length_penalty`
`logprobs`
`max_initial_timestamp_index`
`max_length`
`max_new_tokens`
`max_ngram_size`
`min_new_tokens`
`min_p`
`no_repeat_ngram_size`
`no_timestamps_token_id`
`num_assistant_tokens`
`num_beam_groups`
`num_beams`
`num_return_sequences`
`pad_token_id`
`parsers`
`presence_penalty`
`prev_sot_token_id`
`pruning_ratio`
`relevance_weight`
`repetition_penalty`
`return_omni_outputs`
`return_timestamps`
`rng_seed`
`stop_criteria`
`stop_strings`
`stop_token_ids`
`structured_output_config`
`suppress_tokens`
`task`
`temperature`
`top_k`
`top_p`
`transcribe_token_id`
`translate_token_id`
`tree_depth`	Lookahead depth of the candidate tree
`word_timestamps`

__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__(*args, **kwargs)#

Overloaded function.

__init__(self: openvino_genai.py_openvino_genai.ASRGenerationConfig, json_path: os.PathLike | str | bytes) -> None

path where generation_config.json is stored

__init__(self: openvino_genai.py_openvino_genai.ASRGenerationConfig, **kwargs) -> None

__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_()#

property adapters#

property alignment_heads#

property apply_chat_template#

property assistant_confidence_threshold#

property begin_suppress_tokens#

property branching_factor#: Number of branches (top-k) at each level of the candidate tree

property context#

property decoder_start_token_id#

property diversity_penalty#

property do_sample#

property echo#

property eos_token_id#

property frequency_penalty#

property hotwords#

property ignore_eos#

property include_stop_str_in_output#

property initial_prompt#

is_assisting_generation(self: openvino_genai.py_openvino_genai.GenerationConfig) → bool#

is_beam_search(self: openvino_genai.py_openvino_genai.GenerationConfig) → bool#

is_greedy_decoding(self: openvino_genai.py_openvino_genai.GenerationConfig) → bool#

property is_multilingual#

is_multinomial(self: openvino_genai.py_openvino_genai.GenerationConfig) → bool#

is_prompt_lookup(self: openvino_genai.py_openvino_genai.GenerationConfig) → bool#

is_tree_search(self: openvino_genai.py_openvino_genai.GenerationConfig) → bool#

property lang_to_id#

property language#

property length_penalty#

property logprobs#

property max_initial_timestamp_index#

property max_length#

property max_new_tokens#

property max_ngram_size#

property min_new_tokens#

property min_p#

property no_repeat_ngram_size#

property no_timestamps_token_id#

property num_assistant_tokens#

property num_beam_groups#

property num_beams#

property num_return_sequences#

property pad_token_id#

property parsers#

property presence_penalty#

property prev_sot_token_id#

property pruning_ratio#

property relevance_weight#

property repetition_penalty#

property return_omni_outputs#

property return_timestamps#

property rng_seed#

set_eos_token_id(self: openvino_genai.py_openvino_genai.GenerationConfig, tokenizer_eos_token_id: SupportsInt) → None#

property stop_criteria#

property stop_strings#

property stop_token_ids#

property structured_output_config#

property suppress_tokens#

property task#

property temperature#

property top_k#

property top_p#

property transcribe_token_id#

property translate_token_id#

property tree_depth#: Lookahead depth of the candidate tree

update_generation_config(self: openvino_genai.py_openvino_genai.ASRGenerationConfig, **kwargs) → None#

validate(self: openvino_genai.py_openvino_genai.GenerationConfig) → None#

property word_timestamps#