📘 Overview

The Speech2TextGenerator is an operator designed to transcribe speech content into text. It takes a speech file path or URL as input, utilizes a large language model (LLM) for transcription, and saves the resulting text.

__init__

def __init__(
    self,
    llm_serving: LLMServingABC,
    system_prompt: str = "You are a helpful assistant",
):

Parameter	Type	Default Value	Description
llm_serving	LLMServingABC	Required	The large language model serving instance used for transcription.
system_prompt	str	"You are a helpful assistant"	The system prompt to define the behavior of the model.

Prompt Template Descriptions

Prompt Template Name	Primary Purpose	Applicable Scenarios	Feature Description

run

def run(self, storage: DataFlowStorage, input_key: str = "raw_content", output_key: str = "generated_content"):

Parameter	Type	Default Value	Description
storage	DataFlowStorage	Required	The DataFlow storage instance for reading and writing data.
input_key	str	"raw_content"	The input column name corresponding to the speech file path or URL.
output_key	str	"generated_content"	The output column name for the generated transcription text.

🧠 Example Usage

# Blank

🧾 Default Output Format

Field	Type	Description
raw_content	str	The input speech file path or URL.
generated_content	str	The transcribed text generated by the model.

Example Input:

{
  "raw_content": "path/to/your/audio.mp3"
}

Example Output:

{
  "raw_content": "path/to/your/audio.mp3",
  "generated_content": "This is the transcribed text from the audio file."
}