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
configuration.host = "https://{}.cris.ai".format(SERVICE_REGION)
# 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:
try:
transcription_api.delete_transcription(transcription.id)
except ValueError:
# ignore swagger error on empty response message body: https://github.com/swagger-api/swagger-core/issues/2446
pass
# Specify transcription properties by passing a dict to the properties parameter. See
# https://docs.microsoft.com/azure/cognitive-services/speech-service/batch-transcription#configuration-properties
# for supported parameters.
properties = {
# 'PunctuationMode': 'DictatedAndAutomatic',
# 'ProfanityFilterMode': 'Masked',
# 'AddWordLevelTimestamps': 'False',
# 'AddDiarization': 'False',
# 'AddSentiment': False,
# 'TranscriptionResultsContainerUrl': "<results container>"
}
# Use base models for transcription. Comment this block if you are using a custom model.
transcription_definition = cris_client.TranscriptionDefinition(
name=NAME, description=DESCRIPTION, locale=LOCALE, recordings_url=RECORDINGS_BLOB_URI,
properties=properties
)
# Uncomment this block to use custom models for transcription.
# Model information (ADAPTED_ACOUSTIC_ID and ADAPTED_LANGUAGE_ID) must be set above.
# if ADAPTED_ACOUSTIC_ID is None or ADAPTED_LANGUAGE_ID is None:
# logging.info("Custom model ids must be set to when 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)],
# properties=properties
# )
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_transcription: str = transcription_location.split('/')[-1]
logging.info("Created new transcription with id {}".format(created_transcription))
logging.info("Checking status.")
completed = False
while not completed:
running, not_started = 0, 0
# 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 in ("Failed", "Succeeded"):
# we check to see if it was the transcription we created from this client
if created_transcription != transcription.id:
continue
completed = True
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"))
else:
logging.info("Transcription failed :{}.".format(transcription.status_message))
break
elif transcription.status == "Running":
running += 1
elif transcription.status == "NotStarted":
not_started += 1
logging.info("Transcriptions status: "
"completed (this transcription): {}, {} running, {} not started yet".format(
completed, running, not_started))
# wait for 5 seconds
time.sleep(5)
input("Press any key...")
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
configuration.host = "https://{}.cris.ai".format(SERVICE_REGION)
# 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)
# Use base models for transcription. Comment this block if you are using a custom model.
# Note: you can specify additional transcription properties by passing a
# dictionary in the properties parameter. See
# https://docs.microsoft.com/azure/cognitive-services/speech-service/batch-transcription
# for supported parameters.
transcription_definition = cris_client.TranscriptionDefinition(
name=NAME,
description=DESCRIPTION,
locale=LOCALE,
recordings_url=RECORDINGS_BLOB_URI)
# Uncomment this block to use custom models for transcription.
# Model information (ADAPTED_ACOUSTIC_ID and ADAPTED_LANGUAGE_ID) must be set above.
# if ADAPTED_ACOUSTIC_ID is None or ADAPTED_LANGUAGE_ID is None:
# logging.info("Custom model ids must be set to when 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)]
# )
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_transcription: str = transcription_location.split('/')[-1]
logging.info(
"Created new transcription with id {}".format(created_transcription))
logging.info("Checking status.")
completed = False
while not completed:
running, not_started = 0, 0
# 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 in ("Failed", "Succeeded"):
# we check to see if it was the transcription we created from this client
if created_transcription != transcription.id:
continue
completed = True
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"))
else:
logging.info("Transcription failed :{}.".format(
transcription.status_message))
break
elif transcription.status == "Running":
running += 1
elif transcription.status == "NotStarted":
not_started += 1
logging.info(
"Transcriptions status: "
"completed (this transcription): {}, {} running, {} not started yet"
.format(completed, running, not_started))
# wait for 5 seconds
time.sleep(5)
input("Press any key...")
def transcribe(self,
blob_uri,
name='',
description='',
locale='en-US',
properties={},
output_file=None):
logging.info("Starting transcription client...")
# configure API key authorization: subscription_key
configuration = cris_client.Configuration()
configuration.api_key['Ocp-Apim-Subscription-Key'] = self.speech_key
configuration.host = "https://{}.cris.ai".format(self.service_region)
# 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:
try:
transcription_api.delete_transcription(transcription.id)
except Exception as e:
print(e)
# Specify transcription properties by passing a dict to the properties parameter. See
# https://docs.microsoft.com/azure/cognitive-services/speech-service/batch-transcription#configuration-properties
# for supported parameters.
# properties = {
# 'PunctuationMode': 'DictatedAndAutomatic',
# 'ProfanityFilterMode': 'Masked',
# 'AddWordLevelTimestamps': 'False',
# 'AddDiarization': 'False',
# 'AddSentiment': False,
# 'TranscriptionResultsContainerUrl': "<results container>"
# }
# Use base models for transcription. Comment this block if you are using a custom model.
transcription_definition = cris_client.TranscriptionDefinition(
name=name,
description=description,
locale=locale,
recordings_url=blob_uri,
properties=properties)
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_transcription: str = transcription_location.split('/')[-1]
logging.info("Created new transcription with id {}".format(
created_transcription))
logging.info("Checking status.")
completed = False
while not completed:
running, not_started = 0, 0
# 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 in ("Failed", "Succeeded"):
# we check to see if it was the transcription we created from this client
if created_transcription != transcription.id:
continue
completed = True
if transcription.status == "Succeeded":
results_uri = transcription.results_urls["channel_0"]
results = requests.get(results_uri)
logging.info("Transcription succeeded. Results: ")
logging.info(
"######### TRANSCRIPTION BEGIN ########## ")
logging.info(results.content.decode("utf-8"))
if (output_file):
json_file = open(output_file, 'w')
json_file.write(
json.loads(
json.dumps(results.content.decode("utf-8"),
ensure_ascii=False)))
logging.info("######### TRANSCRIPTION END ########## ")
else:
logging.info("Transcription failed :{}.".format(
transcription.status_message))
break
elif transcription.status == "Running":
running += 1
elif transcription.status == "NotStarted":
not_started += 1
logging.info(
"Transcriptions status: "
"completed (this transcription): {}, {} running, {} not started yet"
.format(completed, running, not_started))
# wait for 5 seconds
time.sleep(5)
def transcribe(url):
logging.info("Starting transcription client...")
# Your subscription key and region for the speech service
SUBSCRIPTION_KEY = ""
SERVICE_REGION = "southcentralus"
NAME = "Simple transcription"
DESCRIPTION = "Simple transcription description"
LOCALE = "en-US"
# Set subscription information when doing transcription with custom models
ADAPTED_ACOUSTIC_ID = None # guid of a custom acoustic model
ADAPTED_LANGUAGE_ID = None # guid of a custom language model
# configure API key authorization: subscription_key
configuration = cris_client.Configuration()
configuration.api_key['Ocp-Apim-Subscription-Key'] = SUBSCRIPTION_KEY
configuration.host = "https://{}.cris.ai".format(SERVICE_REGION)
# 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:
try:
transcription_api.delete_transcription(transcription.id)
except ValueError:
# ignore swagger error on empty response message body: https://github.com/swagger-api/swagger-core/issues/2446
pass
# Use base models for transcription. Comment this block if you are using a custom model.
# Note: you can specify additional transcription properties by passing a
# dictionary in the properties parameter. See
# https://docs.microsoft.com/azure/cognitive-services/speech-service/batch-transcription
# for supported parameters.
logging.info("Printing URL ::: {}".format(url))
transcription_definition = cris_client.TranscriptionDefinition(
name=NAME, description=DESCRIPTION, locale=LOCALE, recordings_url=url
)
# Uncomment this block to use custom models for transcription.
# Model information (ADAPTED_ACOUSTIC_ID and ADAPTED_LANGUAGE_ID) must be set above.
# if ADAPTED_ACOUSTIC_ID is None or ADAPTED_LANGUAGE_ID is None:
# logging.info("Custom model ids must be set to when 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)]
# )
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_transcription: str = transcription_location.split('/')[-1]
logging.info("Created new transcription with id {}".format(created_transcription))
logging.info("Checking status.")
completed = False
while not completed:
running, not_started = 0, 0
# 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 in ("Failed", "Succeeded"):
# we check to see if it was the transcription we created from this client
if created_transcription != transcription.id:
continue
completed = True
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"))
return results.content.decode("utf-8")
else:
logging.info("Transcription failed :{}.".format(transcription.status_message))
break
elif transcription.status == "Running":
running += 1
elif transcription.status == "NotStarted":
not_started += 1
logging.info("Transcriptions status: "
"completed (this transcription): {}, {} running, {} not started yet".format(
completed, running, not_started))
# wait for 5 seconds
time.sleep(5)
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:
try:
transcription_api.delete_transcription(transcription.id)
except ValueError:
# ignore swagger error on empty response message body: https://github.com/swagger-api/swagger-core/issues/2446
pass
logging.info("Creating transcriptions.")
# https://docs.microsoft.com/azure/cognitive-services/speech-service/batch-transcription
properties = {'AddWordLevelTimestamps': 'True', 'AddDiarization': 'True'}
transcription_definition = cris_client.TranscriptionDefinition(
name=NAME,
description=DESCRIPTION,
locale=LOCALE,
recordings_url=RECORDINGS_BLOB_URI,
properties=properties)
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_transcription: str = transcription_location.split('/')[-1]
logging.info("Checking status.")
completed = False
while not completed:
running, not_started = 0, 0
# 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 in ("Failed", "Succeeded"):
# we check to see if it was one of the transcriptions we created from this client
if created_transcription != transcription.id:
continue
completed = True
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"))
else:
logging.info("Transcription failed :{}.".format(
transcription.status_message))
elif transcription.status == "Running":
running += 1
elif transcription.status == "NotStarted":
not_started += 1
logging.info(
"Transcriptions status: "
"completed (this transcription): {}, {} running, {} not started yet"
.format(completed, running, not_started))
time.sleep(5)
sys.exit()
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.")
# Use base models for transcription. Comment this block if you are using a custom model.
transcription_definition = cris_client.TranscriptionDefinition(
name=NAME,
description=DESCRIPTION,
locale=LOCALE,
recordings_url=RECORDINGS_BLOB_URI)
# Uncomment this block to use custom models for transcription.
# Model information (ADAPTED_ACOUSTIC_ID and ADAPTED_LANGUAGE_ID) must be set above.
# if ADAPTED_ACOUSTIC_ID is None or ADAPTED_LANGUAGE_ID is None:
# logging.info("Custom model ids must be set to when 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)]
# )
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_transcription: str = transcription_location.split('/')[-1]
logging.info("Checking status.")
completed = False
running, not_started = 0, 0
while not completed:
# 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 created_transcription != transcription.id:
continue
completed = True
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(
"Transcriptions status: "
"completed (this transcription): {}, {} running, {} not started yet"
.format(completed, running, not_started))
# wait for 5 seconds
time.sleep(5)
input("Press any key...")
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
configuration.host = f"https://{SERVICE_REGION}.api.cognitive.microsoft.com/speechtotext/v3.0"
# create the client object and authenticate
client = cris_client.ApiClient(configuration)
# create an instance of the transcription api class
api = cris_client.CustomSpeechTranscriptionsApi(api_client=client)
# Specify transcription properties by passing a dict to the properties parameter. See
# https://docs.microsoft.com/azure/cognitive-services/speech-service/batch-transcription#configuration-properties
# for supported parameters.
properties = {
# "punctuationMode": "DictatedAndAutomatic",
# "profanityFilterMode": "Masked",
# "wordLevelTimestampsEnabled": True,
# "diarizationEnabled": True,
# "destinationContainerUrl": "<SAS Uri with at least write (w) permissions for an Azure Storage blob container that results should be written to>",
# "timeToLive": "PT1H"
}
# Use base models for transcription. Comment this block if you are using a custom model.
transcription_definition = transcribe_from_single_blob(
RECORDINGS_BLOB_URI, properties)
# Uncomment this block to use custom models for transcription.
# transcription_definition = transcribe_with_custom_model(api, RECORDINGS_BLOB_URI, properties)
# Uncomment this block to transcribe all files from a container.
# transcription_definition = transcribe_from_container(RECORDINGS_CONTAINER_URI, properties)
created_transcription, status, headers = api.create_transcription_with_http_info(
transcription=transcription_definition)
# get the transcription Id from the location URI
transcription_id = headers["location"].split("/")[-1]
# Log information about the created transcription. If you should ask for support, please
# include this information.
logging.info(
f"Created new transcription with id '{transcription_id}' in region {SERVICE_REGION}"
)
logging.info("Checking status.")
completed = False
while not completed:
# wait for 5 seconds before refreshing the transcription status
time.sleep(5)
transcription = api.get_transcription(transcription_id)
logging.info(f"Transcriptions status: {transcription.status}")
if transcription.status in ("Failed", "Succeeded"):
completed = True
if transcription.status == "Succeeded":
pag_files = api.get_transcription_files(transcription_id)
for file_data in _paginate(api, pag_files):
if file_data.kind != "Transcription":
continue
audiofilename = file_data.name
results_url = file_data.links.content_url
results = requests.get(results_url)
logging.info(
f"Results for {audiofilename}:\n{results.content.decode('utf-8')}"
)
elif transcription.status == "Failed":
logging.info(
f"Transcription failed: {transcription.properties.error.message}"
)
def transcribe():
logging.info("Starting transcription client...")
# APIキー認証の構成
configuration = cris_client.Configuration()
configuration.api_key["Ocp-Apim-Subscription-Key"] = SUBSCRIPTION_KEY
configuration.host = "https://{}.cris.ai".format(SERVICE_REGION)
# clientオブジェクトの生成
client = cris_client.ApiClient(configuration)
# transcription apiクラスのインスタンス生成
transcription_api = cris_client.CustomSpeechTranscriptionsApi(
api_client=client)
# ベースモデルを使ったtranscriptionの定義
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)
# locationの取得
transcription_location: str = headers["location"]
# transcription idの取得
created_transcription: str = transcription_location.split("/")[-1]
logging.info(
"Created new transcription with id {}".format(created_transcription))
logging.info("Checking status...")
completed = False
while not completed:
running, not_started = 0, 0
# transcriptionの実行
transcriptions: List[
cris_client.Transcription] = transcription_api.get_transcriptions(
)
for transcription in transcriptions:
if transcription.status in ("Failed", "Succeeded"):
if created_transcription != transcription.id:
continue
completed = True
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"))
else:
logging.info("Transaction failed :{}.".format(
transcription.status_message))
break
elif transcription.status == "Running":
running += 1
elif transcription.status == "NotStarted":
not_started += 1
logging.info(
"Transctions status: "
"completed (this transcription): {}, {} running, {} not started yet"
.format(completed, running, not_started))
time.sleep(5)
input("Press any key...")
def transcribe(outfile, file_name):
block_blob_service = BlockBlobService(account_name=ACCOUNT_NAME,
account_key=ACCOUNT_KEY)
container_name = "youcook2-videos-audio"
blob_name = 'train/' + file_name + '.wav'
sas_url = block_blob_service.generate_blob_shared_access_signature(
container_name,
blob_name,
permission=BlobPermissions.READ,
expiry=datetime.utcnow() + timedelta(hours=1),
start=datetime.utcnow())
print(sas_url)
recordings_blob_uri = URI_PREFIX + '/' + blob_name + '?' + sas_url
print(recordings_blob_uri)
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:
# try:
# transcription_api.delete_transcription(transcription.id)
# except ValueError:
# ignore swagger error on empty response message body: https://github.com/swagger-api/swagger-core/issues/2446
# pass
logging.info("Creating transcriptions.")
# Use base models for transcription. Comment this block if you are using a custom model.
# Note: you can specify additional transcription properties by passing a
# dictionary in the properties parameter. See
# https://docs.microsoft.com/azure/cognitive-services/speech-service/batch-transcription
# for supported parameters.
transcription_definition = cris_client.TranscriptionDefinition(
name=NAME,
description=DESCRIPTION,
locale=LOCALE,
recordings_url=recordings_blob_uri)
# Uncomment this block to use custom models for transcription.
# Model information (ADAPTED_ACOUSTIC_ID and ADAPTED_LANGUAGE_ID) must be set above.
# if ADAPTED_ACOUSTIC_ID is None or ADAPTED_LANGUAGE_ID is None:
# logging.info("Custom model ids must be set to when 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)]
# )
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_transcription: str = transcription_location.split('/')[-1]
logging.info("Checking status.")
completed = False
while not completed:
running, not_started = 0, 0
# 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 in ("Failed", "Succeeded"):
# we check to see if it was one of the transcriptions we created from this client
if created_transcription != transcription.id:
continue
completed = True
if transcription.status == "Succeeded":
results_uri = transcription.results_urls["channel_0"]
results = requests.get(results_uri)
logging.info("Transcription succeeded. Results: ")
with open(outfile, 'w', encoding='utf-8') as f:
json.dump(results.json(),
f,
ensure_ascii=False,
indent=4)
else:
logging.info("Transcription failed :{}.".format(
transcription.status_message))
elif transcription.status == "Running":
running += 1
elif transcription.status == "NotStarted":
not_started += 1
logging.info(
"Transcriptions status: "
"completed (this transcription): {}, {} running, {} not started yet"
.format(completed, running, not_started))
# wait for 10 seconds
time.sleep(10)
