csiebler

        {
            "@odata.type": "#Microsoft.Skills.Text.V3.SentimentSkill",
            "name": "#4",
            "description": null,
            "context": "/document/transcript/*",
            "defaultLanguageCode": "en",
            "modelVersion": null,
            "includeOpinionMining": false,
            "inputs": [
                {

csiebler

<?xml version="1.0" encoding="utf-8"?>
<lexicon xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.w3.org/2005/01/pronunciation-lexicon http://www.w3.org/TR/2007/CR-pronunciation-lexicon-20071212/pls.xsd" version="1.0" alphabet="ipa" xml:lang="de-DE" xmlns="http://www.w3.org/2005/01/pronunciation-lexicon">
  <lexeme>
    <grapheme>passieren</grapheme>
    <phoneme>paˈsiːʁən</phoneme>
  </lexeme>
  <lexeme>
    <grapheme>Reserve</grapheme>
    <phoneme>ʁeˈzɛʁvə</phoneme>
  </lexeme>

csiebler

import azure.cognitiveservices.speech as speechsdk
import requests

# Access key to Speech API from Azure (this needs to be stored in the backend and show not get to the client)
access_key = 'xxxxxxxxxxxx'
region = "westeurope"

# This method should run in the backend, so that access_key is not needed in the client
def get_auth_token(access_key):
    fetch_token_url = f"https://{region}.api.cognitive.microsoft.com/sts/v1.0/issueToken"

csiebler

import requests
import io
import logging
import threading
import time
import concurrent.futures

import Levenshtein as lev
from datetime import datetime

csiebler

import requests
import azure.cognitiveservices.speech as speechsdk

# This code should run in the backend of the mobile application
headers = {
    'Ocp-Apim-Subscription-Key': '<paste your code here>'
}

token_url = 'https://speechapicstest.cognitiveservices.azure.com/sts/v1.0/issuetoken'
response = requests.post(token_url, headers=headers)

csiebler

# This example shows how the real-time Speech API can be used to snythesize audio files that are longer than 10 minutes

import azure.cognitiveservices.speech as speechsdk

speech_key, service_region = "xxxxxxxxxxx", "westeurope"
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)

speech_config.speech_synthesis_voice_name = "de-DE-KatjaNeural"
file_name = "outputaudio.wav"

csiebler

GPT-3 examples (using mostly text-davinci-003)

Information extraction from claim phone conversations

• Engine: text-davinci-003 (also works in text-davinci-002, but might require more instructions to get a correct JSON back)
• Temperature: 0.7

You must extract the following information from the phone conversation below:

csiebler

import os
import openai
from dotenv import load_dotenv
from llama_index import GPTSimpleVectorIndex, SimpleDirectoryReader, LLMPredictor, PromptHelper
from langchain.llms import AzureOpenAI
from langchain.embeddings import OpenAIEmbeddings
from llama_index import LangchainEmbedding

# Load env variables (create .env with OPENAI_API_KEY and OPENAI_API_BASE)
load_dotenv()

csiebler

import os
import openai
from dotenv import load_dotenv
from langchain.llms import AzureOpenAI
from langchain.embeddings import OpenAIEmbeddings

# Load environment variables (set OPENAI_API_KEY, OPENAI_API_BASE, and OPENAI_API_VERSION in .env)
load_dotenv()

# Configure OpenAI API

csiebler

import os
import openai
from dotenv import load_dotenv
from langchain.llms import AzureOpenAI
from langchain.embeddings import OpenAIEmbeddings

# Load environment variables (set OPENAI_API_KEY and OPENAI_API_BASE in .env)
load_dotenv()

# Configure OpenAI API