Я пытаюсь преобразовать аудиофайл разговора в текст с помощью SpeechToText Azure. Я использовал SKD и сделал еще одну попытку с API (следуя этой инструкции https://github.com/Azure-Samples/cognitive-services-speech-sdk/blob/master/samples/batch/python/python-client/main.py), но я также хочу разделить текст результата по разным голосам. Возможно ли это?
Я знаю, что он доступен в бета-версии службы разговоров, но, поскольку мои аудиозаписи на испанском, я не могу их использовать. Есть ли конфигурация для разделения результатов по динамикам?
Это вызов с SDK:
all_results = []
def speech_recognize_continuous_from_file(file_to_transcript):
"""performs continuous speech recognition with input from an audio file"""
# <SpeechContinuousRecognitionWithFile>
speech_config = speechsdk.SpeechConfig(subscription=speech_key,
region=service_region,
speech_recognition_language='es-ES')
audio_config = speechsdk.audio.AudioConfig(filename=file_to_transcribe)
speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)
done = False
def stop_cb(evt):
"""callback that stops continuous recognition upon receiving an event `evt`"""
print('CLOSING on {}'.format(evt))
speech_recognizer.stop_continuous_recognition()
nonlocal done
done = True
# Connect callbacks to the events fired by the speech recognizer
speech_recognizer.recognized.connect(lambda evt: print('RECOGNIZED: {}'.format(evt)))
speech_recognizer.session_started.connect(lambda evt: print('SESSION STARTED: {}'.format(evt)))
speech_recognizer.session_stopped.connect(lambda evt: print('SESSION STOPPED {}'.format(evt)))
speech_recognizer.canceled.connect(lambda evt: print('CANCELED {}'.format(evt)))
# stop continuous recognition on either session stopped or canceled events
speech_recognizer.session_stopped.connect(stop_cb)
speech_recognizer.canceled.connect(stop_cb)
def handle_final_result(evt):
all_results.append(evt.result.text)
speech_recognizer.recognized.connect(handle_final_result)
# Start continuous speech recognition
speech_recognizer.start_continuous_recognition()
while not done:
time.sleep(.5)
# </SpeechContinuousRecognitionWithFile>
И это с API:
from __future__ import print_function
from typing import List
import logging
import sys
import requests
import time
import swagger_client as cris_client
logging.basicConfig(stream=sys.stdout, level=logging.DEBUG, format="%(message)s")
SUBSCRIPTION_KEY = subscription_key
HOST_NAME = "westeurope.cris.ai"
PORT = 443
NAME = "Simple transcription"
DESCRIPTION = "Simple transcription description"
LOCALE = "es-ES"
RECORDINGS_BLOB_URI = bobl_url
# ADAPTED_ACOUSTIC_ID = None # guid of a custom acoustic model
# ADAPTED_LANGUAGE_ID = None # guid of a custom language model
def transcribe():
logging.info("Starting transcription client...")
# configure API key authorization: subscription_key
configuration = cris_client.Configuration()
configuration.api_key['Ocp-Apim-Subscription-Key'] = SUBSCRIPTION_KEY
# create the client object and authenticate
client = cris_client.ApiClient(configuration)
# create an instance of the transcription api class
transcription_api = cris_client.CustomSpeechTranscriptionsApi(api_client=client)
# get all transcriptions for the subscription
transcriptions: List[cris_client.Transcription] = transcription_api.get_transcriptions()
logging.info("Deleting all existing completed transcriptions.")
# delete all pre-existing completed transcriptions
# if transcriptions are still running or not started, they will not be deleted
for transcription in transcriptions:
transcription_api.delete_transcription(transcription.id)
logging.info("Creating transcriptions.")
# transcription definition using custom models
# transcription_definition = cris_client.TranscriptionDefinition(
# name=NAME, description=DESCRIPTION, locale=LOCALE, recordings_url=RECORDINGS_BLOB_URI,
# models=[cris_client.ModelIdentity(ADAPTED_ACOUSTIC_ID), cris_client.ModelIdentity(ADAPTED_LANGUAGE_ID)]
# )
# comment out the previous statement and uncomment the following to use base models for transcription
transcription_definition = cris_client.TranscriptionDefinition(
name=NAME, description=DESCRIPTION, locale=LOCALE, recordings_url=RECORDINGS_BLOB_URI
)
data, status, headers = transcription_api.create_transcription_with_http_info(transcription_definition)
# extract transcription location from the headers
transcription_location: str = headers["location"]
# get the transcription Id from the location URI
created_transcriptions = list()
created_transcriptions.append(transcription_location.split('/')[-1])
logging.info("Checking status.")
completed, running, not_started = 0, 0, 0
while completed < 1:
# get all transcriptions for the user
transcriptions: List[cris_client.Transcription] = transcription_api.get_transcriptions()
# for each transcription in the list we check the status
for transcription in transcriptions:
if transcription.status == "Failed" or transcription.status == "Succeeded":
# we check to see if it was one of the transcriptions we created from this client
if transcription.id not in created_transcriptions:
continue
completed += 1
if transcription.status == "Succeeded":
results_uri = transcription.results_urls["channel_0"]
results = requests.get(results_uri)
logging.info("Transcription succeeded. Results: ")
logging.info(results.content.decode("utf-8"))
elif transcription.status == "Running":
running += 1
elif transcription.status == "NotStarted":
not_started += 1
logging.info(f"Transcriptions status: {completed} completed, {running} running, {not_started} not started yet")
# wait for 5 seconds
time.sleep(5)
input("Press any key...")
def main():
transcribe()
if __name__ == "__main__":
main()