Skip to content

Class swarmauri_standard.llms.WhisperLargeModel.WhisperLargeModel

swarmauri_standard.llms.WhisperLargeModel.WhisperLargeModel

WhisperLargeModel(**data)

Bases: LLMBase

A class implementing OpenAI's Whisper Large V3 model using HuggingFace's Inference API.

This class provides both synchronous and asynchronous methods for transcribing or translating audio files using the Whisper Large V3 model. It supports both single file processing and batch processing with controlled concurrency.

ATTRIBUTE DESCRIPTION
allowed_models

List of supported model identifiers.

TYPE: List[str]

name

The name/identifier of the model being used.

TYPE: str

type

Type identifier for the model.

TYPE: Literal['WhisperLargeModel']

api_key

HuggingFace API key for authentication.

TYPE: str

Link to API KEY: https://huggingface.co/login?next=%2Fsettings%2Ftokens

Example

model = WhisperLargeModel(api_key="your-api-key") text = model.predict("audio.mp3", task="transcription") print(text)

Initialize the WhisperLargeModel instance.

PARAMETER DESCRIPTION
**data

Keyword arguments containing model configuration. Must include 'api_key' for HuggingFace API authentication.

TYPE: Dict[str, Any] DEFAULT: {}

RAISES DESCRIPTION
ValueError

If required configuration parameters are missing.

Source code in swarmauri_standard/llms/WhisperLargeModel.py
55
56
57
58
59
60
61
62
63
64
65
66
67
68
def __init__(self, **data: Dict[str, Any]):
    """
    Initialize the WhisperLargeModel instance.

    Args:
        **data (Dict[str, Any]): Keyword arguments containing model configuration.
               Must include 'api_key' for HuggingFace API authentication.

    Raises:
        ValueError: If required configuration parameters are missing.
    """
    super().__init__(**data)
    self._header = {"Authorization": f"Bearer {self.api_key.get_secret_value()}"}
    self._client = httpx.Client(headers=self._header, timeout=self.timeout)

allowed_models class-attribute instance-attribute

allowed_models = ['openai/whisper-large-v3']

name class-attribute instance-attribute

name = 'openai/whisper-large-v3'

type class-attribute instance-attribute

type = 'WhisperLargeModel'

timeout class-attribute instance-attribute

timeout = 600.0

api_key instance-attribute

api_key

model_config class-attribute instance-attribute

model_config = ConfigDict(
    extra="allow", arbitrary_types_allowed=True
)

id class-attribute instance-attribute

id = Field(default_factory=generate_id)

members class-attribute instance-attribute

members = None

owners class-attribute instance-attribute

owners = None

host class-attribute instance-attribute

host = None

default_logger class-attribute

default_logger = None

logger class-attribute instance-attribute

logger = None

resource class-attribute instance-attribute

resource = Field(default=LLM.value, frozen=True)

version class-attribute instance-attribute

version = '0.1.0'

include_usage class-attribute instance-attribute

include_usage = True

BASE_URL class-attribute instance-attribute

BASE_URL = None

predict

predict(audio_path, task='transcription')

Process a single audio file using the Hugging Face Inference API.

PARAMETER DESCRIPTION
audio_path

Path to the audio file to be processed.

TYPE: str

task

Task to perform. 'transcription': Transcribe audio in its original language. 'translation': Translate audio to English.

TYPE: Literal['transcription', 'translation'] DEFAULT: 'transcription'

RETURNS DESCRIPTION
str

Transcribed or translated text from the audio file.

TYPE: str

RAISES DESCRIPTION
ValueError

If the specified task is not supported.

Exception

If the API response format is unexpected.

HTTPError

If the API request fails.

Source code in swarmauri_standard/llms/WhisperLargeModel.py
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
@retry_on_status_codes((429, 529), max_retries=1)
def predict(
    self,
    audio_path: str,
    task: Literal["transcription", "translation"] = "transcription",
) -> str:
    """
    Process a single audio file using the Hugging Face Inference API.

    Args:
        audio_path (str): Path to the audio file to be processed.
        task (Literal["transcription", "translation"]): Task to perform.
            'transcription': Transcribe audio in its original language.
            'translation': Translate audio to English.

    Returns:
        str: Transcribed or translated text from the audio file.

    Raises:
        ValueError: If the specified task is not supported.
        Exception: If the API response format is unexpected.
        httpx.HTTPError: If the API request fails.
    """
    if task not in ["transcription", "translation"]:
        raise ValueError(
            f"Task {task} not supported. Choose from ['transcription', 'translation']"
        )

    with open(audio_path, "rb") as audio_file:
        data = audio_file.read()

    params = {"task": task}
    if task == "translation":
        params["language"] = "en"

    response = self._client.post(self._BASE_URL, data=data, params=params)
    response.raise_for_status()
    result = response.json()

    if isinstance(result, dict):
        return result.get("text", "")
    elif isinstance(result, list) and len(result) > 0:
        return result[0].get("text", "")
    else:
        raise Exception("Unexpected API response format")

apredict async

apredict(audio_path, task='transcription')

Asynchronously process a single audio file.

This method provides the same functionality as predict() but operates asynchronously for better performance in async contexts.

PARAMETER DESCRIPTION
audio_path

Path to the audio file to be processed.

TYPE: str

task

Task to perform. 'transcription': Transcribe audio in its original language. 'translation': Translate audio to English.

TYPE: Literal['transcription', 'translation'] DEFAULT: 'transcription'

RETURNS DESCRIPTION
str

Transcribed or translated text from the audio file.

TYPE: str

RAISES DESCRIPTION
ValueError

If the specified task is not supported.

Exception

If the API response format is unexpected.

HTTPError

If the API request fails.

Source code in swarmauri_standard/llms/WhisperLargeModel.py
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
@retry_on_status_codes((429, 529), max_retries=1)
async def apredict(
    self,
    audio_path: str,
    task: Literal["transcription", "translation"] = "transcription",
) -> str:
    """
    Asynchronously process a single audio file.

    This method provides the same functionality as `predict()` but operates
    asynchronously for better performance in async contexts.

    Args:
        audio_path (str): Path to the audio file to be processed.
        task (Literal["transcription", "translation"]): Task to perform.
            'transcription': Transcribe audio in its original language.
            'translation': Translate audio to English.

    Returns:
        str: Transcribed or translated text from the audio file.

    Raises:
        ValueError: If the specified task is not supported.
        Exception: If the API response format is unexpected.
        httpx.HTTPError: If the API request fails.
    """
    if task not in ["transcription", "translation"]:
        raise ValueError(
            f"Task {task} not supported. Choose from ['transcription', 'translation']"
        )

    with open(audio_path, "rb") as audio_file:
        data = audio_file.read()

    params = {"task": task}
    if task == "translation":
        params["language"] = "en"

    async with httpx.AsyncClient(headers=self._header) as client:
        response = await client.post(self._BASE_URL, data=data, params=params)
        response.raise_for_status()
        result = response.json()

        if isinstance(result, dict):
            return result.get("text", "")
        elif isinstance(result, list) and len(result) > 0:
            return result[0].get("text", "")
        else:
            raise Exception("Unexpected API response format")

batch

batch(path_task_dict)

Synchronously process multiple audio files.

PARAMETER DESCRIPTION
path_task_dict

Dictionary mapping file paths to their respective tasks. Key: Path to audio file. Value: Task to perform ("transcription" or "translation").

TYPE: Dict[str, Literal['transcription', 'translation']]

RETURNS DESCRIPTION
List[str]

List[str]: List of processed texts, maintaining the order of input files.

Example

files = { ... "file1.mp3": "transcription", ... "file2.mp3": "translation" ... } results = model.batch(files)

Source code in swarmauri_standard/llms/WhisperLargeModel.py
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
def batch(
    self,
    path_task_dict: Dict[str, Literal["transcription", "translation"]],
) -> List[str]:
    """
    Synchronously process multiple audio files.

    Args:
        path_task_dict (Dict[str, Literal["transcription", "translation"]]):
            Dictionary mapping file paths to their respective tasks.
            Key: Path to audio file.
            Value: Task to perform ("transcription" or "translation").

    Returns:
        List[str]: List of processed texts, maintaining the order of input files.

    Example:
        >>> files = {
        ...     "file1.mp3": "transcription",
        ...     "file2.mp3": "translation"
        ... }
        >>> results = model.batch(files)
    """
    return [
        self.predict(audio_path=path, task=task)
        for path, task in path_task_dict.items()
    ]

abatch async

abatch(path_task_dict, max_concurrent=5)

Process multiple audio files in parallel with controlled concurrency.

This method provides the same functionality as batch() but operates asynchronously with controlled concurrency to prevent overwhelming the API or local resources.

PARAMETER DESCRIPTION
path_task_dict

Dictionary mapping file paths to their respective tasks. Key: Path to audio file. Value: Task to perform ("transcription" or "translation").

TYPE: Dict[str, Literal['transcription', 'translation']]

max_concurrent

Maximum number of concurrent requests. Defaults to 5.

TYPE: int DEFAULT: 5

RETURNS DESCRIPTION
List[str]

List[str]: List of processed texts, maintaining the order of input files.

Example

files = { ... "file1.mp3": "transcription", ... "file2.mp3": "translation" ... } results = await model.abatch(files, max_concurrent=3)

Source code in swarmauri_standard/llms/WhisperLargeModel.py
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
async def abatch(
    self,
    path_task_dict: Dict[str, Literal["transcription", "translation"]],
    max_concurrent: int = 5,
) -> List[str]:
    """
    Process multiple audio files in parallel with controlled concurrency.

    This method provides the same functionality as `batch()` but operates
    asynchronously with controlled concurrency to prevent overwhelming
    the API or local resources.

    Args:
        path_task_dict (Dict[str, Literal["transcription", "translation"]]):
            Dictionary mapping file paths to their respective tasks.
            Key: Path to audio file.
            Value: Task to perform ("transcription" or "translation").
        max_concurrent (int, optional): Maximum number of concurrent requests.
            Defaults to 5.

    Returns:
        List[str]: List of processed texts, maintaining the order of input files.

    Example:
        >>> files = {
        ...     "file1.mp3": "transcription",
        ...     "file2.mp3": "translation"
        ... }
        >>> results = await model.abatch(files, max_concurrent=3)
    """
    semaphore = asyncio.Semaphore(max_concurrent)

    async def process_audio(path: str, task: str) -> str:
        async with semaphore:
            return await self.apredict(audio_path=path, task=task)

    tasks = [process_audio(path, task) for path, task in path_task_dict.items()]
    return await asyncio.gather(*tasks)

stream

stream(audio_path, task='transcription')
Source code in swarmauri_standard/llms/WhisperLargeModel.py
233
234
235
236
237
238
def stream(
    self,
    audio_path: str,
    task: Literal["transcription", "translation"] = "transcription",
) -> str:
    raise NotImplementedError("Stream method is not implemented for OpenAIAudio")

astream async

astream(audio_path, task='transcription')
Source code in swarmauri_standard/llms/WhisperLargeModel.py
240
241
242
243
244
245
246
247
async def astream(
    self,
    audio_path: str,
    task: Literal["transcription", "translation"] = "transcription",
) -> str:
    raise NotImplementedError(
        "Asynchrous Stream method is not implemented for OpenAIAudio"
    )

get_allowed_models

get_allowed_models()

Queries the LLMProvider API endpoint to retrieve the list of allowed models.

RETURNS DESCRIPTION
List[str]

List[str]: List of allowed model names.

Source code in swarmauri_standard/llms/WhisperLargeModel.py
249
250
251
252
253
254
255
256
257
def get_allowed_models(self) -> List[str]:
    """
    Queries the LLMProvider API endpoint to retrieve the list of allowed models.

    Returns:
        List[str]: List of allowed model names.
    """
    models_data = ["openai/whisper-large-v3"]
    return models_data

register_model classmethod

register_model()

Decorator to register a base model in the unified registry.

RETURNS DESCRIPTION
Callable

A decorator function that registers the model class.

TYPE: Callable[[Type[BaseModel]], Type[BaseModel]]

Source code in swarmauri_base/DynamicBase.py
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
@classmethod
def register_model(cls) -> Callable[[Type[BaseModel]], Type[BaseModel]]:
    """
    Decorator to register a base model in the unified registry.

    Returns:
        Callable: A decorator function that registers the model class.
    """

    def decorator(model_cls: Type[BaseModel]):
        """Register ``model_cls`` as a base model."""
        model_name = model_cls.__name__
        if model_name in cls._registry:
            glogger.warning(
                "Model '%s' is already registered; skipping duplicate.", model_name
            )
            return model_cls

        cls._registry[model_name] = {"model_cls": model_cls, "subtypes": {}}
        glogger.debug("Registered base model '%s'.", model_name)
        DynamicBase._recreate_models()
        return model_cls

    return decorator

register_type classmethod

register_type(resource_type=None, type_name=None)

Decorator to register a subtype under one or more base models in the unified registry.

PARAMETER DESCRIPTION
resource_type

The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase) are used.

TYPE: Optional[Union[Type[T], List[Type[T]]]] DEFAULT: None

type_name

An optional custom type name for the subtype.

TYPE: Optional[str] DEFAULT: None

RETURNS DESCRIPTION
Callable

A decorator function that registers the subtype.

TYPE: Callable[[Type[DynamicBase]], Type[DynamicBase]]

Source code in swarmauri_base/DynamicBase.py
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
@classmethod
def register_type(
    cls,
    resource_type: Optional[Union[Type[T], List[Type[T]]]] = None,
    type_name: Optional[str] = None,
) -> Callable[[Type["DynamicBase"]], Type["DynamicBase"]]:
    """
    Decorator to register a subtype under one or more base models in the unified registry.

    Parameters:
        resource_type (Optional[Union[Type[T], List[Type[T]]]]):
            The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase)
            are used.
        type_name (Optional[str]): An optional custom type name for the subtype.

    Returns:
        Callable: A decorator function that registers the subtype.
    """

    def decorator(subclass: Type["DynamicBase"]):
        """Register ``subclass`` as a subtype."""
        if resource_type is None:
            resource_types = [
                base for base in subclass.__bases__ if base is not cls
            ]
        elif not isinstance(resource_type, list):
            resource_types = [resource_type]
        else:
            resource_types = resource_type

        for rt in resource_types:
            if not issubclass(subclass, rt):
                raise TypeError(
                    f"'{subclass.__name__}' must be a subclass of '{rt.__name__}'."
                )
            final_type_name = type_name or getattr(
                subclass, "_type", subclass.__name__
            )
            base_model_name = rt.__name__

            if base_model_name not in cls._registry:
                cls._registry[base_model_name] = {"model_cls": rt, "subtypes": {}}
                glogger.debug(
                    "Created new registry entry for base model '%s'.",
                    base_model_name,
                )

            subtypes_dict = cls._registry[base_model_name]["subtypes"]
            if final_type_name in subtypes_dict:
                glogger.warning(
                    "Type '%s' already exists under '%s'; skipping duplicate.",
                    final_type_name,
                    base_model_name,
                )
                continue

            subtypes_dict[final_type_name] = subclass
            glogger.debug(
                "Registered '%s' as '%s' under '%s'.",
                subclass.__name__,
                final_type_name,
                base_model_name,
            )

        DynamicBase._recreate_models()
        return subclass

    return decorator

model_validate_toml classmethod

model_validate_toml(toml_data)

Validate a model from a TOML string.

Source code in swarmauri_base/TomlMixin.py
12
13
14
15
16
17
18
19
20
21
22
23
24
@classmethod
def model_validate_toml(cls, toml_data: str):
    """Validate a model from a TOML string."""
    try:
        # Parse TOML into a Python dictionary
        toml_content = tomllib.loads(toml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(toml_content))
    except tomllib.TOMLDecodeError as e:
        raise ValueError(f"Invalid TOML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_toml

model_dump_toml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a TOML representation of the model.

Source code in swarmauri_base/TomlMixin.py
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
def model_dump_toml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a TOML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into TOML
    return toml.dumps(filtered_data)

model_validate_yaml classmethod

model_validate_yaml(yaml_data)

Validate a model from a YAML string.

Source code in swarmauri_base/YamlMixin.py
11
12
13
14
15
16
17
18
19
20
21
22
23
@classmethod
def model_validate_yaml(cls, yaml_data: str):
    """Validate a model from a YAML string."""
    try:
        # Parse YAML into a Python dictionary
        yaml_content = yaml.safe_load(yaml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(yaml_content))
    except yaml.YAMLError as e:
        raise ValueError(f"Invalid YAML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_yaml

model_dump_yaml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a YAML representation of the model.

Source code in swarmauri_base/YamlMixin.py
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
def model_dump_yaml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a YAML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into YAML using safe mode
    return yaml.safe_dump(filtered_data, default_flow_style=False)

model_post_init

model_post_init(logger=None)

Assign a logger instance after model initialization.

Source code in swarmauri_base/LoggerMixin.py
23
24
25
26
27
28
def model_post_init(self, logger: Optional[FullUnion[LoggerBase]] = None) -> None:
    """Assign a logger instance after model initialization."""

    # Directly assign the provided FullUnion[LoggerBase] or fallback to the
    # class-level default.
    self.logger = self.logger or logger or self.default_logger

add_allowed_model

add_allowed_model(model)

Add a new model to the list of allowed models.

RAISES DESCRIPTION
ValueError

If the model is already in the allowed models list.

Source code in swarmauri_base/llms/LLMBase.py
36
37
38
39
40
41
42
43
44
45
def add_allowed_model(self, model: str) -> None:
    """
    Add a new model to the list of allowed models.

    Raises:
        ValueError: If the model is already in the allowed models list.
    """
    if model in self.allowed_models:
        raise ValueError(f"Model '{model}' is already allowed.")
    self.allowed_models.append(model)

remove_allowed_model

remove_allowed_model(model)

Remove a model from the list of allowed models.

RAISES DESCRIPTION
ValueError

If the model is not in the allowed models list.

Source code in swarmauri_base/llms/LLMBase.py
47
48
49
50
51
52
53
54
55
56
def remove_allowed_model(self, model: str) -> None:
    """
    Remove a model from the list of allowed models.

    Raises:
        ValueError: If the model is not in the allowed models list.
    """
    if model not in self.allowed_models:
        raise ValueError(f"Model '{model}' is not in the allowed models list.")
    self.allowed_models.remove(model)