YandexSTTParser#
- class langchain_community.document_loaders.parsers.audio.YandexSTTParser(*, api_key: str | None = None, iam_token: str | None = None, model: str = 'general', language: str = 'auto')[source]#
Transcribe and parse audio files. Audio transcription is with OpenAI Whisper model.
Initialize the parser.
- Parameters:
api_key (str | None) – API key for a service account
role. (with the ai.speechkit-stt.user)
iam_token (str | None) – IAM token for a service account
role.
model (str) – Recognition model name. Defaults to general.
language (str) – The language in ISO 639-1 format. Defaults to automatic language recognition.
Either api_key or iam_token must be provided, but not both.
Methods
__init__
(*[, api_key, iam_token, model, ...])Initialize the parser.
lazy_parse
(blob)Lazily parse the blob.
parse
(blob)Eagerly parse the blob into a document or documents.
- __init__(*, api_key: str | None = None, iam_token: str | None = None, model: str = 'general', language: str = 'auto')[source]#
Initialize the parser.
- Parameters:
api_key (str | None) – API key for a service account
role. (with the ai.speechkit-stt.user)
iam_token (str | None) – IAM token for a service account
role.
model (str) – Recognition model name. Defaults to general.
language (str) – The language in ISO 639-1 format. Defaults to automatic language recognition.
Either api_key or iam_token must be provided, but not both.