本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。
使用 SDK 进行转录 AWS
不论是批量转录还是流式转录，您都可以使用 SDK。如果您要转录 Amazon S3 存储桶中的媒体文件，则是在执行批量转录。如果您要转录音频数据的实时流，则将执行流式转录。
有关可与之配合使用的编程语言的列表 Amazon Transcribe，请参阅支持的编程语言。请注意，并非所有 AWS SDK 都支持流式转录。要查看支持的媒体格式以及其它媒体要求和限制，请参阅数据输入和输出。
有关所有可用的 AWS SDK 和构建器工具的更多信息，请参阅构建工具。 AWS
您可以使用 Amazon S3
存储桶中的媒体文件的 URI 创建批量转录。如果您不确定如何创建 Amazon S3 存储桶或上传文件，请参阅创建您的第一个 S3 存储桶和将对象上传到您的存储桶。
- Java
-
import software.amazon.awssdk.auth.credentials.AwsCredentialsProvider;
import software.amazon.awssdk.auth.credentials.DefaultCredentialsProvider;
import software.amazon.awssdk.regions.Region;
import software.amazon.awssdk.services.transcribe.TranscribeClient;
import software.amazon.awssdk.services.transcribe.model.*;
import software.amazon.awssdk.services.transcribestreaming.model.LanguageCode;
public class TranscribeDemoApp {
private static final Region REGION = Region.US_WEST_2;
private static TranscribeClient client;
public static void main(String args[]) {
client = TranscribeClient.builder()
.credentialsProvider(getCredentials())
.region(REGION)
.build();
String transcriptionJobName = "my-first-transcription-job";
String mediaType = "flac"; // can be other types
Media myMedia = Media.builder()
.mediaFileUri("s3://DOC-EXAMPLE-BUCKET/my-input-files/my-media-file.flac")
.build();
String outputS3BucketName = "s3://DOC-EXAMPLE-BUCKET";
// Create the transcription job request
StartTranscriptionJobRequest request = StartTranscriptionJobRequest.builder()
.transcriptionJobName(transcriptionJobName)
.languageCode(LanguageCode.EN_US.toString())
.mediaSampleRateHertz(16000)
.mediaFormat(mediaType)
.media(myMedia)
.outputBucketName(outputS3BucketName)
.build();
// send the request to start the transcription job
StartTranscriptionJobResponse startJobResponse = client.startTranscriptionJob(request);
System.out.println("Created the transcription job");
System.out.println(startJobResponse.transcriptionJob());
// Create the get job request
GetTranscriptionJobRequest getJobRequest = GetTranscriptionJobRequest.builder()
.transcriptionJobName(transcriptionJobName)
.build();
// send the request to get the transcription job including the job status
GetTranscriptionJobResponse getJobResponse = client.getTranscriptionJob(getJobRequest);
System.out.println("Get the transcription job request");
System.out.println(getJobResponse.transcriptionJob());
}
private static AwsCredentialsProvider getCredentials() {
return DefaultCredentialsProvider.create();
}
}
- JavaScript
-
const { TranscribeClient, StartTranscriptionJobCommand } = require("@aws-sdk/client-transcribe"); // CommonJS import
const region = "us-west-2";
const credentials = {
"accessKeyId": "",
"secretAccessKey": "",
};
const input = {
TranscriptionJobName: "my-first-transcription-job",
LanguageCode: "en-US",
Media: {
MediaFileUri: "s3://DOC-EXAMPLE-BUCKET/my-input-files/my-media-file.flac"
},
OutputBucketName: "DOC-EXAMPLE-BUCKET",
};
async function startTranscriptionRequest() {
const transcribeConfig = {
region,
credentials
};
const transcribeClient = new TranscribeClient(transcribeConfig);
const transcribeCommand = new StartTranscriptionJobCommand(input);
try {
const transcribeResponse = await transcribeClient.send(transcribeCommand);
console.log("Transcription job created, the details:");
console.log(transcribeResponse.TranscriptionJob);
} catch(err) {
console.log(err);
}
}
startTranscriptionRequest();
- Python
-
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 = 'flac',
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', region_name = 'us-west-2')
file_uri = 's3://DOC-EXAMPLE-BUCKET/my-input-files/my-media-file.flac'
transcribe_file('Example-job', file_uri, transcribe_client)
if __name__ == '__main__':
main()
您可以使用流媒体文件或实时媒体流来创建流式转录。
请注意， Amazon Transcribe 流媒体 AWS SDK for Python (Boto3) 不支持该标准。要使用 Python 开始直播转录，请将此异步 Python SDK 用于。 Amazon Transcribe
- Java
-
以下示例是一个转录流音频的 Java 程序。
要运行此示例，请注意以下条件：
另请参阅：重试用于 Amazon Transcribe 直播的客户端 (Java SDK)。该代码管理与 Amazon Transcribe 的连接，并在连接出错时重试发送数据。例如，如果网络出现临时错误，则此客户端将重新发送失败的请求。
public class TranscribeStreamingDemoApp {
private static final Region REGION = Region.US_WEST_2;
private static TranscribeStreamingAsyncClient client;
public static void main(String args[]) throws URISyntaxException, ExecutionException, InterruptedException, LineUnavailableException {
client = TranscribeStreamingAsyncClient.builder()
.credentialsProvider(getCredentials())
.region(REGION)
.build();
CompletableFuture<Void> result = client.startStreamTranscription(getRequest(16_000),
new AudioStreamPublisher(getStreamFromMic()),
getResponseHandler());
result.get();
client.close();
}
private static InputStream getStreamFromMic() throws LineUnavailableException {
// Signed PCM AudioFormat with 16,000 Hz, 16 bit sample size, mono
int sampleRate = 16000;
AudioFormat format = new AudioFormat(sampleRate, 16, 1, true, false);
DataLine.Info info = new DataLine.Info(TargetDataLine.class, format);
if (!AudioSystem.isLineSupported(info)) {
System.out.println("Line not supported");
System.exit(0);
}
TargetDataLine line = (TargetDataLine) AudioSystem.getLine(info);
line.open(format);
line.start();
InputStream audioStream = new AudioInputStream(line);
return audioStream;
}
private static AwsCredentialsProvider getCredentials() {
return DefaultCredentialsProvider.create();
}
private static StartStreamTranscriptionRequest getRequest(Integer mediaSampleRateHertz) {
return StartStreamTranscriptionRequest.builder()
.languageCode(LanguageCode.EN_US.toString())
.mediaEncoding(MediaEncoding.PCM)
.mediaSampleRateHertz(mediaSampleRateHertz)
.build();
}
private static StartStreamTranscriptionResponseHandler getResponseHandler() {
return StartStreamTranscriptionResponseHandler.builder()
.onResponse(r -> {
System.out.println("Received Initial response");
})
.onError(e -> {
System.out.println(e.getMessage());
StringWriter sw = new StringWriter();
e.printStackTrace(new PrintWriter(sw));
System.out.println("Error Occurred: " + sw.toString());
})
.onComplete(() -> {
System.out.println("=== All records stream successfully ===");
})
.subscriber(event -> {
List<Result> results = ((TranscriptEvent) event).transcript().results();
if (results.size() > 0) {
if (!results.get(0).alternatives().get(0).transcript().isEmpty()) {
System.out.println(results.get(0).alternatives().get(0).transcript());
}
}
})
.build();
}
private InputStream getStreamFromFile(String myMediaFileName) {
try {
File inputFile = new File(getClass().getClassLoader().getResource(myMediaFileName).getFile());
InputStream audioStream = new FileInputStream(inputFile);
return audioStream;
} catch (FileNotFoundException e) {
throw new RuntimeException(e);
}
}
private static class AudioStreamPublisher implements Publisher<AudioStream> {
private final InputStream inputStream;
private static Subscription currentSubscription;
private AudioStreamPublisher(InputStream inputStream) {
this.inputStream = inputStream;
}
@Override
public void subscribe(Subscriber<? super AudioStream> s) {
if (this.currentSubscription == null) {
this.currentSubscription = new SubscriptionImpl(s, inputStream);
} else {
this.currentSubscription.cancel();
this.currentSubscription = new SubscriptionImpl(s, inputStream);
}
s.onSubscribe(currentSubscription);
}
}
public static class SubscriptionImpl implements Subscription {
private static final int CHUNK_SIZE_IN_BYTES = 1024 * 1;
private final Subscriber<? super AudioStream> subscriber;
private final InputStream inputStream;
private ExecutorService executor = Executors.newFixedThreadPool(1);
private AtomicLong demand = new AtomicLong(0);
SubscriptionImpl(Subscriber<? super AudioStream> s, InputStream inputStream) {
this.subscriber = s;
this.inputStream = inputStream;
}
@Override
public void request(long n) {
if (n <= 0) {
subscriber.onError(new IllegalArgumentException("Demand must be positive"));
}
demand.getAndAdd(n);
executor.submit(() -> {
try {
do {
ByteBuffer audioBuffer = getNextEvent();
if (audioBuffer.remaining() > 0) {
AudioEvent audioEvent = audioEventFromBuffer(audioBuffer);
subscriber.onNext(audioEvent);
} else {
subscriber.onComplete();
break;
}
} while (demand.decrementAndGet() > 0);
} catch (Exception e) {
subscriber.onError(e);
}
});
}
@Override
public void cancel() {
executor.shutdown();
}
private ByteBuffer getNextEvent() {
ByteBuffer audioBuffer = null;
byte[] audioBytes = new byte[CHUNK_SIZE_IN_BYTES];
int len = 0;
try {
len = inputStream.read(audioBytes);
if (len <= 0) {
audioBuffer = ByteBuffer.allocate(0);
} else {
audioBuffer = ByteBuffer.wrap(audioBytes, 0, len);
}
} catch (IOException e) {
throw new UncheckedIOException(e);
}
return audioBuffer;
}
private AudioEvent audioEventFromBuffer(ByteBuffer bb) {
return AudioEvent.builder()
.audioChunk(SdkBytes.fromByteBuffer(bb))
.build();
}
}
}
- JavaScript
-
const {
TranscribeStreamingClient,
StartStreamTranscriptionCommand,
} = require("@aws-sdk/client-transcribe-streaming");
const { createReadStream } = require("fs");
const { join } = require("path");
const audio = createReadStream(join(__dirname, "my-media-file.flac"), { highWaterMark: 1024 * 16});
const LanguageCode = "en-US";
const MediaEncoding = "pcm";
const MediaSampleRateHertz = "16000";
const credentials = {
"accessKeyId": "",
"secretAccessKey": "",
};
async function startRequest() {
const client = new TranscribeStreamingClient({
region: "us-west-2",
credentials
});
const params = {
LanguageCode,
MediaEncoding,
MediaSampleRateHertz,
AudioStream: (async function* () {
for await (const chunk of audio) {
yield {AudioEvent: {AudioChunk: chunk}};
}
})(),
};
const command = new StartStreamTranscriptionCommand(params);
// Send transcription request
const response = await client.send(command);
// Start to print response
try {
for await (const event of response.TranscriptResultStream) {
console.log(JSON.stringify(event));
}
} catch(err) {
console.log("error")
console.log(err)
}
}
startRequest();
- Python
-
以下示例是一个转录流音频的 Python 程序。
要运行此示例，请注意以下条件：
import asyncio
# This example uses aiofile for asynchronous file reads.
# It's not a dependency of the project but can be installed
# with `pip install aiofile`.
import aiofile
from amazon_transcribe.client import TranscribeStreamingClient
from amazon_transcribe.handlers import TranscriptResultStreamHandler
from amazon_transcribe.model import TranscriptEvent
"""
Here's an example of a custom event handler you can extend to
process the returned transcription results as needed. This
handler will simply print the text out to your interpreter.
"""
class MyEventHandler(TranscriptResultStreamHandler):
async def handle_transcript_event(self, transcript_event: TranscriptEvent):
# This handler can be implemented to handle transcriptions as needed.
# Here's an example to get started.
results = transcript_event.transcript.results
for result in results:
for alt in result.alternatives:
print(alt.transcript)
async def basic_transcribe():
# Set up our client with your chosen Region
client = TranscribeStreamingClient(region = "us-west-2")
# Start transcription to generate async stream
stream = await client.start_stream_transcription(
language_code = "en-US",
media_sample_rate_hz = 16000,
media_encoding = "pcm",
)
async def write_chunks():
# NOTE: For pre-recorded files longer than 5 minutes, the sent audio
# chunks should be rate limited to match the real-time bitrate of the
# audio stream to avoid signing issues.
async with aiofile.AIOFile('filepath/my-media-file.flac', 'rb') as afp:
reader = aiofile.Reader(afp, chunk_size = 1024 * 16)
async for chunk in reader:
await stream.input_stream.send_audio_event(audio_chunk = chunk)
await stream.input_stream.end_stream()
# Instantiate our handler and start processing events
handler = MyEventHandler(stream.output_stream)
await asyncio.gather(write_chunks(), handler.handle_events())
loop = asyncio.get_event_loop()
loop.run_until_complete(basic_transcribe())
loop.close()
- C++
-
有关流式转录 C++ SDK 示例的信息，请参阅代码示例章节。
AWS 软件开发套件 (SDK) 可用于许多流行的编程语言。每个软件开发工具包都提供 API、代码示例和文档，使开发人员能够更轻松地以其首选语言构建应用程序。
有关特定于此服务的示例，请参阅使用软件开发工具包的 Amazon Transcribe 的代码示例 AWS。
找不到所需的内容？ 通过使用此页面底部的提供反馈链接请求代码示例。
