Sono disponibili altri esempi AWS SDK nel repository [AWS Doc SDK](https://github.com/awsdocs/aws-doc-sdk-examples) Examples. GitHub
Le traduzioni sono generate tramite traduzione automatica. In caso di conflitto tra il contenuto di una traduzione e la versione originale in Inglese, quest'ultima prevarrà.
# Esempi per Amazon Transcribe con SDK per Python (Boto3)
I seguenti esempi di codice mostrano come eseguire azioni e implementare scenari comuni utilizzando Amazon Transcribe. AWS SDK per Python (Boto3)
Le *azioni* sono estratti di codice da programmi più grandi e devono essere eseguite nel contesto. Sebbene le azioni mostrino come richiamare le singole funzioni del servizio, è possibile visualizzarle contestualizzate negli scenari correlati.
*Scenari*: esempi di codice che mostrano come eseguire un’attività specifica chiamando più funzioni all’interno dello stesso servizio o combinate con altri Servizi AWS.
Ogni esempio include un link al codice sorgente completo, in cui vengono fornite le istruzioni su come configurare ed eseguire il codice nel contesto.
**Topics**
+ [Azioni](#actions)
+ [Scenari](#scenarios)
## Azioni
### `CreateVocabulary`
Il seguente esempio di codice mostra come usare. `CreateVocabulary`
**SDK per Python (Boto3)**
C'è altro da fare GitHub. Trova l'esempio completo e scopri di più sulla configurazione e l'esecuzione nel [Repository di esempi di codice AWS](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/transcribe#code-examples).
```
def create_vocabulary(
vocabulary_name, language_code, transcribe_client, phrases=None, table_uri=None
):
"""
Creates a custom vocabulary that can be used to improve the accuracy of
transcription jobs. This function returns as soon as the vocabulary processing
is started. Call get_vocabulary to get the current status of the vocabulary.
The vocabulary is ready to use when its status is 'READY'.
:param vocabulary_name: The name of the custom vocabulary.
:param language_code: The language code of the vocabulary.
For example, en-US or nl-NL.
:param transcribe_client: The Boto3 Transcribe client.
:param phrases: A list of comma-separated phrases to include in the vocabulary.
:param table_uri: A table of phrases and pronunciation hints to include in the
vocabulary.
:return: Information about the newly created vocabulary.
"""
try:
vocab_args = {"VocabularyName": vocabulary_name, "LanguageCode": language_code}
if phrases is not None:
vocab_args["Phrases"] = phrases
elif table_uri is not None:
vocab_args["VocabularyFileUri"] = table_uri
response = transcribe_client.create_vocabulary(**vocab_args)
logger.info("Created custom vocabulary %s.", response["VocabularyName"])
except ClientError:
logger.exception("Couldn't create custom vocabulary %s.", vocabulary_name)
raise
else:
return response
```
+ Per i dettagli sull'API, consulta [CreateVocabulary AWS](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/CreateVocabulary)*SDK for Python (Boto3) API Reference*.
### `DeleteTranscriptionJob`
Il seguente esempio di codice mostra come utilizzare. `DeleteTranscriptionJob`
**SDK per Python (Boto3)**
C'è altro da fare GitHub. Trova l'esempio completo e scopri di più sulla configurazione e l'esecuzione nel [Repository di esempi di codice AWS](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/transcribe#code-examples).
```
def delete_job(job_name, transcribe_client):
"""
Deletes a transcription job. This also deletes the transcript associated with
the job.
:param job_name: The name of the job to delete.
:param transcribe_client: The Boto3 Transcribe client.
"""
try:
transcribe_client.delete_transcription_job(TranscriptionJobName=job_name)
logger.info("Deleted job %s.", job_name)
except ClientError:
logger.exception("Couldn't delete job %s.", job_name)
raise
```
+ Per i dettagli sull'API, consulta [DeleteTranscriptionJob AWS](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/DeleteTranscriptionJob)*SDK for Python (Boto3) API Reference*.
### `DeleteVocabulary`
Il seguente esempio di codice mostra come utilizzare. `DeleteVocabulary`
**SDK per Python (Boto3)**
C'è altro da fare GitHub. Trova l'esempio completo e scopri di più sulla configurazione e l'esecuzione nel [Repository di esempi di codice AWS](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/transcribe#code-examples).
```
def delete_vocabulary(vocabulary_name, transcribe_client):
"""
Deletes a custom vocabulary.
:param vocabulary_name: The name of the vocabulary to delete.
:param transcribe_client: The Boto3 Transcribe client.
"""
try:
transcribe_client.delete_vocabulary(VocabularyName=vocabulary_name)
logger.info("Deleted vocabulary %s.", vocabulary_name)
except ClientError:
logger.exception("Couldn't delete vocabulary %s.", vocabulary_name)
raise
```
+ Per i dettagli sull'API, consulta [DeleteVocabulary AWS](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/DeleteVocabulary)*SDK for Python (Boto3) API Reference*.
### `GetTranscriptionJob`
Il seguente esempio di codice mostra come utilizzare. `GetTranscriptionJob`
**SDK per Python (Boto3)**
C'è altro da fare GitHub. Trova l'esempio completo e scopri di più sulla configurazione e l'esecuzione nel [Repository di esempi di codice AWS](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/transcribe#code-examples).
```
def get_job(job_name, transcribe_client):
"""
Gets details about a transcription job.
:param job_name: The name of the job to retrieve.
:param transcribe_client: The Boto3 Transcribe client.
:return: The retrieved transcription job.
"""
try:
response = transcribe_client.get_transcription_job(
TranscriptionJobName=job_name
)
job = response["TranscriptionJob"]
logger.info("Got job %s.", job["TranscriptionJobName"])
except ClientError:
logger.exception("Couldn't get job %s.", job_name)
raise
else:
return job
```
+ Per i dettagli sull'API, consulta [GetTranscriptionJob AWS](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/GetTranscriptionJob)*SDK for Python (Boto3) API Reference*.
### `GetVocabulary`
Il seguente esempio di codice mostra come utilizzare. `GetVocabulary`
**SDK per Python (Boto3)**
C'è altro da fare GitHub. Trova l'esempio completo e scopri di più sulla configurazione e l'esecuzione nel [Repository di esempi di codice AWS](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/transcribe#code-examples).
```
def get_vocabulary(vocabulary_name, transcribe_client):
"""
Gets information about a custom vocabulary.
:param vocabulary_name: The name of the vocabulary to retrieve.
:param transcribe_client: The Boto3 Transcribe client.
:return: Information about the vocabulary.
"""
try:
response = transcribe_client.get_vocabulary(VocabularyName=vocabulary_name)
logger.info("Got vocabulary %s.", response["VocabularyName"])
except ClientError:
logger.exception("Couldn't get vocabulary %s.", vocabulary_name)
raise
else:
return response
```
+ Per i dettagli sull'API, consulta [GetVocabulary AWS](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/GetVocabulary)*SDK for Python (Boto3) API Reference*.
### `ListTranscriptionJobs`
Il seguente esempio di codice mostra come utilizzare. `ListTranscriptionJobs`
**SDK per Python (Boto3)**
C'è altro da fare GitHub. Trova l'esempio completo e scopri di più sulla configurazione e l'esecuzione nel [Repository di esempi di codice AWS](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/transcribe#code-examples).
```
def list_jobs(job_filter, transcribe_client):
"""
Lists summaries of the transcription jobs for the current AWS account.
:param job_filter: The list of returned jobs must contain this string in their
names.
:param transcribe_client: The Boto3 Transcribe client.
:return: The list of retrieved transcription job summaries.
"""
try:
response = transcribe_client.list_transcription_jobs(JobNameContains=job_filter)
jobs = response["TranscriptionJobSummaries"]
next_token = response.get("NextToken")
while next_token is not None:
response = transcribe_client.list_transcription_jobs(
JobNameContains=job_filter, NextToken=next_token
)
jobs += response["TranscriptionJobSummaries"]
next_token = response.get("NextToken")
logger.info("Got %s jobs with filter %s.", len(jobs), job_filter)
except ClientError:
logger.exception("Couldn't get jobs with filter %s.", job_filter)
raise
else:
return jobs
```
+ Per i dettagli sull'API, consulta [ListTranscriptionJobs AWS](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/ListTranscriptionJobs)*SDK for Python (Boto3) API Reference*.
### `ListVocabularies`
Il seguente esempio di codice mostra come utilizzare. `ListVocabularies`
**SDK per Python (Boto3)**
C'è altro da fare GitHub. Trova l'esempio completo e scopri di più sulla configurazione e l'esecuzione nel [Repository di esempi di codice AWS](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/transcribe#code-examples).
```
def list_vocabularies(vocabulary_filter, transcribe_client):
"""
Lists the custom vocabularies created for this AWS account.
:param vocabulary_filter: The returned vocabularies must contain this string in
their names.
:param transcribe_client: The Boto3 Transcribe client.
:return: The list of retrieved vocabularies.
"""
try:
response = transcribe_client.list_vocabularies(NameContains=vocabulary_filter)
vocabs = response["Vocabularies"]
next_token = response.get("NextToken")
while next_token is not None:
response = transcribe_client.list_vocabularies(
NameContains=vocabulary_filter, NextToken=next_token
)
vocabs += response["Vocabularies"]
next_token = response.get("NextToken")
logger.info(
"Got %s vocabularies with filter %s.", len(vocabs), vocabulary_filter
)
except ClientError:
logger.exception(
"Couldn't list vocabularies with filter %s.", vocabulary_filter
)
raise
else:
return vocabs
```
+ Per i dettagli sull'API, consulta [ListVocabularies AWS](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/ListVocabularies)*SDK for Python (Boto3) API Reference*.
### `StartTranscriptionJob`
Il seguente esempio di codice mostra come utilizzare. `StartTranscriptionJob`
**SDK per Python (Boto3)**
C'è altro da fare GitHub. Trova l'esempio completo e scopri di più sulla configurazione e l'esecuzione nel [Repository di esempi di codice AWS](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/transcribe#code-examples).
```
def start_job(
job_name,
media_uri,
media_format,
language_code,
transcribe_client,
vocabulary_name=None,
):
"""
Starts a transcription job. This function returns as soon as the job is started.
To get the current status of the job, call get_transcription_job. The job is
successfully completed when the job status is 'COMPLETED'.
:param job_name: The name of the transcription job. This must be unique for
your AWS account.
:param media_uri: The URI where the audio file is stored. This is typically
in an Amazon S3 bucket.
:param media_format: The format of the audio file. For example, mp3 or wav.
:param language_code: The language code of the audio file.
For example, en-US or ja-JP
:param transcribe_client: The Boto3 Transcribe client.
:param vocabulary_name: The name of a custom vocabulary to use when transcribing
the audio file.
:return: Data about the job.
"""
try:
job_args = {
"TranscriptionJobName": job_name,
"Media": {"MediaFileUri": media_uri},
"MediaFormat": media_format,
"LanguageCode": language_code,
}
if vocabulary_name is not None:
job_args["Settings"] = {"VocabularyName": vocabulary_name}
response = transcribe_client.start_transcription_job(**job_args)
job = response["TranscriptionJob"]
logger.info("Started transcription job %s.", job_name)
except ClientError:
logger.exception("Couldn't start transcription job %s.", job_name)
raise
else:
return job
```
+ Per i dettagli sull'API, consulta [StartTranscriptionJob AWS](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/StartTranscriptionJob)*SDK for Python (Boto3) API Reference*.
### `UpdateVocabulary`
Il seguente esempio di codice mostra come utilizzare. `UpdateVocabulary`
**SDK per Python (Boto3)**
C'è altro da fare GitHub. Trova l'esempio completo e scopri di più sulla configurazione e l'esecuzione nel [Repository di esempi di codice AWS](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/transcribe#code-examples).
```
def update_vocabulary(
vocabulary_name, language_code, transcribe_client, phrases=None, table_uri=None
):
"""
Updates an existing custom vocabulary. The entire vocabulary is replaced with
the contents of the update.
:param vocabulary_name: The name of the vocabulary to update.
:param language_code: The language code of the vocabulary.
:param transcribe_client: The Boto3 Transcribe client.
:param phrases: A list of comma-separated phrases to include in the vocabulary.
:param table_uri: A table of phrases and pronunciation hints to include in the
vocabulary.
"""
try:
vocab_args = {"VocabularyName": vocabulary_name, "LanguageCode": language_code}
if phrases is not None:
vocab_args["Phrases"] = phrases
elif table_uri is not None:
vocab_args["VocabularyFileUri"] = table_uri
response = transcribe_client.update_vocabulary(**vocab_args)
logger.info("Updated custom vocabulary %s.", response["VocabularyName"])
except ClientError:
logger.exception("Couldn't update custom vocabulary %s.", vocabulary_name)
raise
```
+ Per i dettagli sull'API, consulta [UpdateVocabulary AWS](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/UpdateVocabulary)*SDK for Python (Boto3) API Reference*.
## Scenari
### Crea e perfezionate un vocabolario personalizzato
L’esempio di codice seguente mostra come:
+ Caricare un file audio in Amazon S3.
+ Eseguire un processo Amazon Transcribe per trascrivere il file e ottenere i risultati.
+ Creare e perfezionare un vocabolario personalizzato per migliorare l’accuratezza della trascrizione.
+ Eseguire i processi con vocabolari personalizzati e ottenere i risultati.
**SDK per Python (Boto3)**
C'è di più su. GitHub Trova l'esempio completo e scopri di più sulla configurazione e l'esecuzione nel [Repository di esempi di codice AWS](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/transcribe#code-examples).
Trascrivere un file audio che contiene una lettura di Jabberwocky di Lewis Carroll. Iniziare creando funzioni che racchiudono le azioni di Amazon Transcribe.
```
def start_job(
job_name,
media_uri,
media_format,
language_code,
transcribe_client,
vocabulary_name=None,
):
"""
Starts a transcription job. This function returns as soon as the job is started.
To get the current status of the job, call get_transcription_job. The job is
successfully completed when the job status is 'COMPLETED'.
:param job_name: The name of the transcription job. This must be unique for
your AWS account.
:param media_uri: The URI where the audio file is stored. This is typically
in an Amazon S3 bucket.
:param media_format: The format of the audio file. For example, mp3 or wav.
:param language_code: The language code of the audio file.
For example, en-US or ja-JP
:param transcribe_client: The Boto3 Transcribe client.
:param vocabulary_name: The name of a custom vocabulary to use when transcribing
the audio file.
:return: Data about the job.
"""
try:
job_args = {
"TranscriptionJobName": job_name,
"Media": {"MediaFileUri": media_uri},
"MediaFormat": media_format,
"LanguageCode": language_code,
}
if vocabulary_name is not None:
job_args["Settings"] = {"VocabularyName": vocabulary_name}
response = transcribe_client.start_transcription_job(**job_args)
job = response["TranscriptionJob"]
logger.info("Started transcription job %s.", job_name)
except ClientError:
logger.exception("Couldn't start transcription job %s.", job_name)
raise
else:
return job
def get_job(job_name, transcribe_client):
"""
Gets details about a transcription job.
:param job_name: The name of the job to retrieve.
:param transcribe_client: The Boto3 Transcribe client.
:return: The retrieved transcription job.
"""
try:
response = transcribe_client.get_transcription_job(
TranscriptionJobName=job_name
)
job = response["TranscriptionJob"]
logger.info("Got job %s.", job["TranscriptionJobName"])
except ClientError:
logger.exception("Couldn't get job %s.", job_name)
raise
else:
return job
def delete_job(job_name, transcribe_client):
"""
Deletes a transcription job. This also deletes the transcript associated with
the job.
:param job_name: The name of the job to delete.
:param transcribe_client: The Boto3 Transcribe client.
"""
try:
transcribe_client.delete_transcription_job(TranscriptionJobName=job_name)
logger.info("Deleted job %s.", job_name)
except ClientError:
logger.exception("Couldn't delete job %s.", job_name)
raise
def create_vocabulary(
vocabulary_name, language_code, transcribe_client, phrases=None, table_uri=None
):
"""
Creates a custom vocabulary that can be used to improve the accuracy of
transcription jobs. This function returns as soon as the vocabulary processing
is started. Call get_vocabulary to get the current status of the vocabulary.
The vocabulary is ready to use when its status is 'READY'.
:param vocabulary_name: The name of the custom vocabulary.
:param language_code: The language code of the vocabulary.
For example, en-US or nl-NL.
:param transcribe_client: The Boto3 Transcribe client.
:param phrases: A list of comma-separated phrases to include in the vocabulary.
:param table_uri: A table of phrases and pronunciation hints to include in the
vocabulary.
:return: Information about the newly created vocabulary.
"""
try:
vocab_args = {"VocabularyName": vocabulary_name, "LanguageCode": language_code}
if phrases is not None:
vocab_args["Phrases"] = phrases
elif table_uri is not None:
vocab_args["VocabularyFileUri"] = table_uri
response = transcribe_client.create_vocabulary(**vocab_args)
logger.info("Created custom vocabulary %s.", response["VocabularyName"])
except ClientError:
logger.exception("Couldn't create custom vocabulary %s.", vocabulary_name)
raise
else:
return response
def get_vocabulary(vocabulary_name, transcribe_client):
"""
Gets information about a custom vocabulary.
:param vocabulary_name: The name of the vocabulary to retrieve.
:param transcribe_client: The Boto3 Transcribe client.
:return: Information about the vocabulary.
"""
try:
response = transcribe_client.get_vocabulary(VocabularyName=vocabulary_name)
logger.info("Got vocabulary %s.", response["VocabularyName"])
except ClientError:
logger.exception("Couldn't get vocabulary %s.", vocabulary_name)
raise
else:
return response
def update_vocabulary(
vocabulary_name, language_code, transcribe_client, phrases=None, table_uri=None
):
"""
Updates an existing custom vocabulary. The entire vocabulary is replaced with
the contents of the update.
:param vocabulary_name: The name of the vocabulary to update.
:param language_code: The language code of the vocabulary.
:param transcribe_client: The Boto3 Transcribe client.
:param phrases: A list of comma-separated phrases to include in the vocabulary.
:param table_uri: A table of phrases and pronunciation hints to include in the
vocabulary.
"""
try:
vocab_args = {"VocabularyName": vocabulary_name, "LanguageCode": language_code}
if phrases is not None:
vocab_args["Phrases"] = phrases
elif table_uri is not None:
vocab_args["VocabularyFileUri"] = table_uri
response = transcribe_client.update_vocabulary(**vocab_args)
logger.info("Updated custom vocabulary %s.", response["VocabularyName"])
except ClientError:
logger.exception("Couldn't update custom vocabulary %s.", vocabulary_name)
raise
def list_vocabularies(vocabulary_filter, transcribe_client):
"""
Lists the custom vocabularies created for this AWS account.
:param vocabulary_filter: The returned vocabularies must contain this string in
their names.
:param transcribe_client: The Boto3 Transcribe client.
:return: The list of retrieved vocabularies.
"""
try:
response = transcribe_client.list_vocabularies(NameContains=vocabulary_filter)
vocabs = response["Vocabularies"]
next_token = response.get("NextToken")
while next_token is not None:
response = transcribe_client.list_vocabularies(
NameContains=vocabulary_filter, NextToken=next_token
)
vocabs += response["Vocabularies"]
next_token = response.get("NextToken")
logger.info(
"Got %s vocabularies with filter %s.", len(vocabs), vocabulary_filter
)
except ClientError:
logger.exception(
"Couldn't list vocabularies with filter %s.", vocabulary_filter
)
raise
else:
return vocabs
def delete_vocabulary(vocabulary_name, transcribe_client):
"""
Deletes a custom vocabulary.
:param vocabulary_name: The name of the vocabulary to delete.
:param transcribe_client: The Boto3 Transcribe client.
"""
try:
transcribe_client.delete_vocabulary(VocabularyName=vocabulary_name)
logger.info("Deleted vocabulary %s.", vocabulary_name)
except ClientError:
logger.exception("Couldn't delete vocabulary %s.", vocabulary_name)
raise
```
Richiamare le funzioni wrapper per trascrivere l’audio senza un vocabolario personalizzato e poi con diverse versioni di un vocabolario personalizzato per ottenere risultati migliori.
```
def usage_demo():
"""Shows how to use the Amazon Transcribe service."""
logging.basicConfig(level=logging.INFO, format="%(levelname)s: %(message)s")
s3_resource = boto3.resource("s3")
transcribe_client = boto3.client("transcribe")
print("-" * 88)
print("Welcome to the Amazon Transcribe demo!")
print("-" * 88)
bucket_name = f"jabber-bucket-{time.time_ns()}"
print(f"Creating bucket {bucket_name}.")
bucket = s3_resource.create_bucket(
Bucket=bucket_name,
CreateBucketConfiguration={
"LocationConstraint": transcribe_client.meta.region_name
},
)
media_file_name = ".media/Jabberwocky.mp3"
media_object_key = "Jabberwocky.mp3"
print(f"Uploading media file {media_file_name}.")
bucket.upload_file(media_file_name, media_object_key)
media_uri = f"s3://{bucket.name}/{media_object_key}"
job_name_simple = f"Jabber-{time.time_ns()}"
print(f"Starting transcription job {job_name_simple}.")
start_job(
job_name_simple,
f"s3://{bucket_name}/{media_object_key}",
"mp3",
"en-US",
transcribe_client,
)
transcribe_waiter = TranscribeCompleteWaiter(transcribe_client)
transcribe_waiter.wait(job_name_simple)
job_simple = get_job(job_name_simple, transcribe_client)
transcript_simple = requests.get(
job_simple["Transcript"]["TranscriptFileUri"]
).json()
print(f"Transcript for job {transcript_simple['jobName']}:")
print(transcript_simple["results"]["transcripts"][0]["transcript"])
print("-" * 88)
print(
"Creating a custom vocabulary that lists the nonsense words to try to "
"improve the transcription."
)
vocabulary_name = f"Jabber-vocabulary-{time.time_ns()}"
create_vocabulary(
vocabulary_name,
"en-US",
transcribe_client,
phrases=[
"brillig",
"slithy",
"borogoves",
"mome",
"raths",
"Jub-Jub",
"frumious",
"manxome",
"Tumtum",
"uffish",
"whiffling",
"tulgey",
"thou",
"frabjous",
"callooh",
"callay",
"chortled",
],
)
vocabulary_ready_waiter = VocabularyReadyWaiter(transcribe_client)
vocabulary_ready_waiter.wait(vocabulary_name)
job_name_vocabulary_list = f"Jabber-vocabulary-list-{time.time_ns()}"
print(f"Starting transcription job {job_name_vocabulary_list}.")
start_job(
job_name_vocabulary_list,
media_uri,
"mp3",
"en-US",
transcribe_client,
vocabulary_name,
)
transcribe_waiter.wait(job_name_vocabulary_list)
job_vocabulary_list = get_job(job_name_vocabulary_list, transcribe_client)
transcript_vocabulary_list = requests.get(
job_vocabulary_list["Transcript"]["TranscriptFileUri"]
).json()
print(f"Transcript for job {transcript_vocabulary_list['jobName']}:")
print(transcript_vocabulary_list["results"]["transcripts"][0]["transcript"])
print("-" * 88)
print(
"Updating the custom vocabulary with table data that provides additional "
"pronunciation hints."
)
table_vocab_file = "jabber-vocabulary-table.txt"
bucket.upload_file(table_vocab_file, table_vocab_file)
update_vocabulary(
vocabulary_name,
"en-US",
transcribe_client,
table_uri=f"s3://{bucket.name}/{table_vocab_file}",
)
vocabulary_ready_waiter.wait(vocabulary_name)
job_name_vocab_table = f"Jabber-vocab-table-{time.time_ns()}"
print(f"Starting transcription job {job_name_vocab_table}.")
start_job(
job_name_vocab_table,
media_uri,
"mp3",
"en-US",
transcribe_client,
vocabulary_name=vocabulary_name,
)
transcribe_waiter.wait(job_name_vocab_table)
job_vocab_table = get_job(job_name_vocab_table, transcribe_client)
transcript_vocab_table = requests.get(
job_vocab_table["Transcript"]["TranscriptFileUri"]
).json()
print(f"Transcript for job {transcript_vocab_table['jobName']}:")
print(transcript_vocab_table["results"]["transcripts"][0]["transcript"])
print("-" * 88)
print("Getting data for jobs and vocabularies.")
jabber_jobs = list_jobs("Jabber", transcribe_client)
print(f"Found {len(jabber_jobs)} jobs:")
for job_sum in jabber_jobs:
job = get_job(job_sum["TranscriptionJobName"], transcribe_client)
print(
f"\t{job['TranscriptionJobName']}, {job['Media']['MediaFileUri']}, "
f"{job['Settings'].get('VocabularyName')}"
)
jabber_vocabs = list_vocabularies("Jabber", transcribe_client)
print(f"Found {len(jabber_vocabs)} vocabularies:")
for vocab_sum in jabber_vocabs:
vocab = get_vocabulary(vocab_sum["VocabularyName"], transcribe_client)
vocab_content = requests.get(vocab["DownloadUri"]).text
print(f"\t{vocab['VocabularyName']} contents:")
print(vocab_content)
print("-" * 88)
print("Deleting demo jobs.")
for job_name in [job_name_simple, job_name_vocabulary_list, job_name_vocab_table]:
delete_job(job_name, transcribe_client)
print("Deleting demo vocabulary.")
delete_vocabulary(vocabulary_name, transcribe_client)
print("Deleting demo bucket.")
bucket.objects.delete()
bucket.delete()
print("Thanks for watching!")
```
+ Per informazioni dettagliate sull’API, consulta i seguenti argomenti nella *documentazione di riferimento dell’API AWS SDK per Python (Boto3)*.
+ [CreateVocabulary](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/CreateVocabulary)
+ [DeleteTranscriptionJob](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/DeleteTranscriptionJob)
+ [DeleteVocabulary](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/DeleteVocabulary)
+ [GetTranscriptionJob](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/GetTranscriptionJob)
+ [GetVocabulary](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/GetVocabulary)
+ [ListVocabularies](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/ListVocabularies)
+ [StartTranscriptionJob](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/StartTranscriptionJob)
+ [UpdateVocabulary](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/UpdateVocabulary)
### Trascrivere l’audio e ottenere i dati di processo
L’esempio di codice seguente mostra come:
+ Avviare un processo di trascrizione con Amazon Transcribe.
+ Attendi il completamento del processo.
+ Ottenere l’URI in cui è archiviata la trascrizione.
Per ulteriori informazioni, consulta [Nozioni di base su Amazon Transcribe](https://docs.aws.amazon.com/transcribe/latest/dg/getting-started.html).
**SDK per Python (Boto3)**
C'è dell'altro GitHub. Trova l'esempio completo e scopri di più sulla configurazione e l'esecuzione nel [Repository di esempi di codice AWS](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/transcribe#code-examples).
```
import time
import boto3
def transcribe_file(job_name, file_uri, transcribe_client):
transcribe_client.start_transcription_job(
TranscriptionJobName=job_name,
Media={"MediaFileUri": file_uri},
MediaFormat="wav",
LanguageCode="en-US",
)
max_tries = 60
while max_tries > 0:
max_tries -= 1
job = transcribe_client.get_transcription_job(TranscriptionJobName=job_name)
job_status = job["TranscriptionJob"]["TranscriptionJobStatus"]
if job_status in ["COMPLETED", "FAILED"]:
print(f"Job {job_name} is {job_status}.")
if job_status == "COMPLETED":
print(
f"Download the transcript from\n"
f"\t{job['TranscriptionJob']['Transcript']['TranscriptFileUri']}."
)
break
else:
print(f"Waiting for {job_name}. Current status is {job_status}.")
time.sleep(10)
def main():
transcribe_client = boto3.client("transcribe")
file_uri = "s3://test-transcribe/answer2.wav"
transcribe_file("Example-job", file_uri, transcribe_client)
if __name__ == "__main__":
main()
```
+ Per informazioni dettagliate sull’API, consulta i seguenti argomenti nella *documentazione di riferimento dell’API AWS SDK per Python (Boto3)*.
+ [GetTranscriptionJob](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/GetTranscriptionJob)
+ [StartTranscriptionJob](https://docs.aws.amazon.com/goto/boto3/transcribe-2017-10-26/StartTranscriptionJob)