AudioModelInference

class ibm_watsonx_ai.foundation_models.inference.AudioModelInference(model, credentials=None, project_id=None, space_id=None, verify=None, api_client=None)

Bases: WMLResource

Instantiate the audio model interface

Parameters:

• model (str, optional) – type of model to use

• credentials (Credentials or dict, optional) – credentials for the Watson Machine Learning instance

• project_id (str, optional) – ID of the Watson Studio project

• space_id (str, optional) – ID of the Watson Studio space

• verify (bool or str, optional) –

  You can pass one of the following as verify:

  • the path to a CA_BUNDLE file

  • the path of directory with certificates of trusted CAs

  • True - default path to truststore will be taken

  • False - no verification will be made

• api_client (APIClient, optional) – initialized APIClient object with a set project ID or space ID. If passed, credentials and project_id/space_id are not required.

Example:

from ibm_watsonx_ai import Credentials
from ibm_watsonx_ai.foundation_models import AudioModelInference

audio_model = AudioModelInference(
    model="<AUDIO MODEL>",
    credentials=Credentials(
        api_key = IAM_API_KEY,
        url = "https://us-south.ml.cloud.ibm.com"
    ),
    project_id=project_id
)

transcribe(file_path, language=None)

Transcribe audio into text.

Parameters:

• file_path (str, Path, required) – The path to the audio file to transcribe

• language (str, optional) – Target language to which to transcribe, e.g. ‘fr’ for French. Default is English.

Example:

file_path = "sample_audio.mp3"

response = audio_model.transcribe(file_path=file_path)

Enums

class AudioTranscriptionsModels

Bases: StrEnum

This represents a dynamically generated Enum for Audio Transcriptions Foundation Models.

Example of getting AudioTranscriptionsModels:

# GET AudioTranscriptionsModels ENUM
client.foundation_models.AudioTranscriptionsModels

# PRINT dict of Enums
client.foundation_models.AudioTranscriptionsModels.show()

Example Output:

{'WHISPER_TINY': 'openai/whisper-tiny'}

Example of initialising ModelInference with AudioTranscriptionsModels Enum:

from ibm_watsonx_ai.foundation_models import AudioModelInference

model = AudioModelInference(
    model_id=client.foundation_models.AudioTranscriptionsModels.WHISPER_TINY,
    credentials=Credentials(...),
    project_id=project_id,
)