Summary

Enable this model configuration to get the extractive summary of the video/audio.

Overview

This model extracts the key sentences used in the video/audio and summarizes them .

modelTypeConfiguration

Keys	Value
modelType	extractive_summary
modelConfig	Model Configuration object for extractive_summary(No configurations)

Example Request

Curl

curl --location --request POST 'https://api.marsview.ai/cb/v1/conversation/compute' \
--header 'Content-Type: application/json' \
--header "Authorization: {{Insert Auth Token}}" \
--data-raw '{
        "txnId": "{{Insert txn ID}}",
        "enableModels":[
            {
            "modelType":"speech_to_text",
                "modelConfig":{
                    "automatic_punctuation" : true,
                    "custom_vocabulary":["Marsview", "Communication"],
                    "speaker_seperation":{
                        "num_speakers":2
                    },
                    "enableKeywords":true,
                    "enableTopics":false
                    }
            },
            {
            "modelType":"extractive_summary"
            }
        ]
}'

Python

import requests
auth_token = "replace this with your auth token"
txn_id = "Replace this with your txn id"
request_url = "https://api.marsview.ai/cb/v1/conversation/compute"


def get_extractive_summary():
  payload={
        "txnId": txn_id,
        "enableModels":[
            {
            "modelType":"speech_to_text",
                "modelConfig":{
                    "automatic_punctuation" : True,
                    "custom_vocabulary":["Marsview", "Communication"],
                    "speaker_seperation":{
                        "num_speakers":2
                    },
                    "enableKeywords":True,
                    "enableTopics":False
                }
            },
            {
            "modelType":"extractive_summary"
            },
            ]
        }
  headers = {'authorization': '{}'.format(auth_token)}
  
  response = requests.request("POST", headers=headers, json=payload)
  print(response.text)
  if response.status_code == 200 and response.json()["status"] == "true":
    return response.json()["data"]["enableModels"]["state"]["status"]
  else:
    raise Exception("Custom exception")

if __name__ == "__main__": 
    get_extractive_summary()

Response

"data": {
    "summaryData": [
        {
            "sentence": "I will start by asking a few questions and then give you an opportunity to ask any questions you may have at the end.",
            "startTime": 6600,
            "endTime": 12950,
            "speaker": "1"
        },
    ]
}

Response Object

Field	Description
summaryData	List of key sentences identified in the Video/Audio
sentence	A sentence identified by the model in the given time frame.
startTime	Start time of the sentence in the input Video/Audio in milliseconds.
endTime	End time of the sentence in the input Video/Audio in milliseconds.
speaker	Id of the speaker whose voice is identified in the given time frame. (Will return a String "unknown" if the speaker could not be identified or speaker separation is set to -1(disabled).