langchain_community.document_loaders.parsers.audio.OpenAIWhisperParserLocal¶
- class langchain_community.document_loaders.parsers.audio.OpenAIWhisperParserLocal(device: str = '0', lang_model: Optional[str] = None, batch_size: int = 8, chunk_length: int = 30, forced_decoder_ids: Optional[Tuple[Dict]] = None)[source]¶
Transcribe and parse audio files with OpenAI Whisper model.
Audio transcription with OpenAI Whisper model locally from transformers.
Parameters: device - device to use
NOTE: By default uses the gpu if available, if you want to use cpu, please set device = “cpu”
lang_model - whisper model to use, for example “openai/whisper-medium” forced_decoder_ids - id states for decoder in multilanguage model,
usage example: from transformers import WhisperProcessor processor = WhisperProcessor.from_pretrained(“openai/whisper-medium”) forced_decoder_ids = WhisperProcessor.get_decoder_prompt_ids(language=”french”,
task=”transcribe”)
forced_decoder_ids = WhisperProcessor.get_decoder_prompt_ids(language=”french”, task=”translate”)
Initialize the parser.
- Parameters
device (str) – device to use.
lang_model (Optional[str]) – whisper model to use, for example “openai/whisper-medium”. Defaults to None.
forced_decoder_ids (Optional[Tuple[Dict]]) – id states for decoder in a multilanguage model. Defaults to None.
batch_size (int) – batch size used for decoding Defaults to 8.
chunk_length (int) – chunk length used during inference. Defaults to 30s.
Methods
__init__([device, lang_model, batch_size, ...])Initialize the parser.
lazy_parse(blob)Lazily parse the blob.
parse(blob)Eagerly parse the blob into a document or documents.
- __init__(device: str = '0', lang_model: Optional[str] = None, batch_size: int = 8, chunk_length: int = 30, forced_decoder_ids: Optional[Tuple[Dict]] = None)[source]¶
Initialize the parser.
- Parameters
device (str) – device to use.
lang_model (Optional[str]) – whisper model to use, for example “openai/whisper-medium”. Defaults to None.
forced_decoder_ids (Optional[Tuple[Dict]]) – id states for decoder in a multilanguage model. Defaults to None.
batch_size (int) – batch size used for decoding Defaults to 8.
chunk_length (int) – chunk length used during inference. Defaults to 30s.