RoxanaTapia

{
   "pairwiseDiffs":[
      {
         "fileA":"among-us-baseline.txt",
         "fileB":"among-us-correct.mp3",
         "granularity":"word",
         "differences":[
            {
               "position":0,
               "segmentFromA":"I",

RoxanaTapia

[
   {
      "fileA":"among-us-baseline.txt",
      "fileB":"among-us-correct.mp3",
      "granularity":"word",
      "differences":[
         {
            "position":0,
            "segmentFromA":"I",
            "segmentFromB":"I",

RoxanaTapia

{
   "name":"among-us-speech",
   "sources":[
      {
         "filename":"among-us-baseline.txt",
         "segments":[
            "I",
            "was",
            "playing",
            "Among",

RoxanaTapia

[
   {
      "filename":"among-us-baseline.txt",
      "location":"./source/media/among-us-baseline.txt",
      "media_type":"txt",
      "extractor":"read",
      "transcript":"I was playing Among Us and I wasn’t the imposter. Everybody voted that I was the imposter. So I can’t continue playing."
   },
   {
      "filename":"among-us-correct.mp3",

RoxanaTapia

[
   {
      "filename":"among-us-correct.mp3",
      "location":"https://s3.amazonaws.com/pinocchio-inputs/among-us-correct.mp3",
      "media_type":"mp3",
      "job":"among-us-speech-among-us-correct.mp3",
      "status":"COMPLETED",
      "transcript":"I was playing among us and I was the imposter. Everybody voted that I wasn't the imposter, so I can continue playing.",
      "metadata":{
         "jobName":"among-us-speech-among-us-correct.mp3",

RoxanaTapia

[
   {
      "filename":"among-us-baseline.txt",
      "location":"./source/media/among-us-baseline.txt",
      "media_type":"txt",
      "extractor":"read",
      "transcript":"I was playing Among Us and I wasn’t the imposter. Everybody voted that I was the imposter. So I can’t continue playing."
   }
]

RoxanaTapia

# abstraction component configurations
# plugins are paths to their respective plugins
# impl are classes that can be imported from plugins module
extract_transcripts:
  plugins: extract_transcripts.plugins
  impl: AWSTranscribe
  # input is a directory filled with media files
  input: ./source/media
  # output is a directory to write the output JSON to
  output: ./outputs/extract_transcripts