Google Speech-to-Text API Speaker Diarization with Python .long_running_recognize() method

Question

I was following the answer in this question. But my audio is more then 1 min so I have to use .long_running_recognize(config, audio) method instead .recognize(config, audio). Here is the code:

from pathlib import Path
#  https://cloud.google.com/python/docs/reference/speech/latest/google.cloud.speech_v1p1beta1.services.speech.SpeechClient
from google.cloud import speech_v1p1beta1 as speech
from google.cloud import storage

def file_upload(client, file: Path, bucket_name: str = 'wav_files_ua_eu_standard'):
    # https://stackoverflow.com/questions/62125584/file-upload-using-pythonlocal-system-to-google-cloud-storage#:~:text=You%20can%20do%20it%20in%20this%20way%2C%20from,string%20of%20text%20blob.upload_from_string%20%28%27this%20is%20test%20content%21%27%29

    bucket = client.get_bucket(bucket_name)
    blob = bucket.blob(file.name)
    # Uploading from local file without open()
    blob.upload_from_filename(file)
    # https://cloud.google.com/python/docs/reference/storage/latest/google.cloud.storage.blob.Blob   
    uri3 = 'gs://' + blob.id[:-(len(str(blob.generation)) + 1)]
    print(F"{uri3=}")
    return uri3


client = speech.SpeechClient()
client_bucket = storage.Client(project='my-project-id-is-hidden')
speech_file_name = R"C:\Users\vasil\OneDrive\wav_samples\wav_sample_phone_call.wav"
speech_file = Path(speech_file_name)

if speech_file.exists:
    uri = file_upload(client_bucket, speech_file)

# audio = speech.RecognitionAudio(content=content)  
audio = speech.RecognitionAudio(uri=uri) 

diarization_config = speech.SpeakerDiarizationConfig(
    enable_speaker_diarization=True,
    min_speaker_count=2,
    max_speaker_count=3,
)

config = speech.RecognitionConfig(
    encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
    sample_rate_hertz=8000,
    language_code="ru-RU",   # "uk-UA",  "ru-RU",
    # alternative_language_codes=["uk-UA", ],
    diarization_config=diarization_config,
)

print("Waiting for operation to complete...")
# response = client.recognize(config=config, audio=audio)
response = client.long_running_recognize(config=config, audio=audio)
   
words_info = result.results

# Printing out the output:
for word_info in words_info[0].alternatives[0].words:
    print(f"word: '{word_info.word}', speaker_tag: {word_info.speaker_tag}")

The differences are

• I have to upload the file for recognitions and get URI uploaded file
• use speech.RecognitionAudio(uri=uri) - not .RecognitionAudio(content=content)
• use client.long_running_recognize(config=config, audio=audio) - not client.recognize(config=config, audio=audio)

So the code is working - but... Result has no information about diariztion labels... What I am doing wrong? Here is output, speaker_tag always is equal to zero.

word: 'Алло', speaker_tag: 0
word: 'здравствуйте', speaker_tag: 0
word: 'Я', speaker_tag: 0
word: 'хочу', speaker_tag: 0
word: 'котёнок', speaker_tag: 0
word: 'Ты', speaker_tag: 0
word: 'очень', speaker_tag: 0
word: 'классная', speaker_tag: 0
word: 'Спасибо', speaker_tag: 0
word: 'приятно', speaker_tag: 0
word: 'что', speaker_tag: 0
word: 'вы', speaker_tag: 0
word: 'и', speaker_tag: 0
word: 'Хорошего', speaker_tag: 0
word: 'вам', speaker_tag: 0
word: 'дня', speaker_tag: 0
word: 'сегодня', speaker_tag: 0
word: 'Спасибо', speaker_tag: 0
word: 'до', speaker_tag: 0
word: 'свидания', speaker_tag: 0

Answer 1

The problrm was in only 1 number in statement

for word_info in words_info[0].alternatives[0].words:

correct way is:

for word_info in words_info[-1].alternatives[0].words:

and all works properly. To get all the words with speaker tags, you only have to take the words list from the last result.