Lokale Audiodatei, die mehr als einen Kanal umfasst, transkribieren.
Weitere Informationen
Eine ausführliche Dokumentation, die dieses Codebeispiel enthält, finden Sie hier:
Codebeispiel
Java
/**
* Transcribe a local audio file with multi-channel recognition
*
* @param fileName the path to local audio file
*/
public static void transcribeMultiChannel(String fileName) throws Exception {
Path path = Paths.get(fileName);
byte[] content = Files.readAllBytes(path);
try (SpeechClient speechClient = SpeechClient.create()) {
// Get the contents of the local audio file
RecognitionAudio recognitionAudio =
RecognitionAudio.newBuilder().setContent(ByteString.copyFrom(content)).build();
// Configure request to enable multiple channels
RecognitionConfig config =
RecognitionConfig.newBuilder()
.setEncoding(AudioEncoding.LINEAR16)
.setLanguageCode("en-US")
.setSampleRateHertz(44100)
.setAudioChannelCount(2)
.setEnableSeparateRecognitionPerChannel(true)
.build();
// Perform the transcription request
RecognizeResponse recognizeResponse = speechClient.recognize(config, recognitionAudio);
// Print out the results
for (SpeechRecognitionResult result : recognizeResponse.getResultsList()) {
// There can be several alternative transcripts for a given chunk of speech. Just use the
// first (most likely) one here.
SpeechRecognitionAlternative alternative = result.getAlternatives(0);
System.out.format("Transcript : %s\n", alternative.getTranscript());
System.out.printf("Channel Tag : %s\n", result.getChannelTag());
}
}
}
Node.js
const fs = require('fs');
// Imports the Google Cloud client library
const speech = require('@google-cloud/speech').v1;
// Creates a client
const client = new speech.SpeechClient();
/**
* TODO(developer): Uncomment the following lines before running the sample.
*/
// const fileName = 'Local path to audio file, e.g. /path/to/audio.raw';
const config = {
encoding: 'LINEAR16',
languageCode: 'en-US',
audioChannelCount: 2,
enableSeparateRecognitionPerChannel: true,
};
const audio = {
content: fs.readFileSync(fileName).toString('base64'),
};
const request = {
config: config,
audio: audio,
};
const [response] = await client.recognize(request);
const transcription = response.results
.map(
result =>
` Channel Tag: ${result.channelTag} ${result.alternatives[0].transcript}`
)
.join('\n');
console.log(`Transcription: \n${transcription}`);
Python
from google.cloud import speech
client = speech.SpeechClient()
with open(speech_file, "rb") as audio_file:
content = audio_file.read()
audio = speech.RecognitionAudio(content=content)
config = speech.RecognitionConfig(
encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=44100,
language_code="en-US",
audio_channel_count=2,
enable_separate_recognition_per_channel=True,
)
response = client.recognize(config=config, audio=audio)
for i, result in enumerate(response.results):
alternative = result.alternatives[0]
print("-" * 20)
print("First alternative of result {}".format(i))
print(u"Transcript: {}".format(alternative.transcript))
print(u"Channel Tag: {}".format(result.channel_tag))
Ruby
# audio_file_path = "path/to/audio.wav"
require "google/cloud/speech"
speech = Google::Cloud::Speech.speech
config = {
encoding: :LINEAR16,
sample_rate_hertz: 44_100,
language_code: "en-US",
audio_channel_count: 2,
enable_separate_recognition_per_channel: true
}
audio_file = File.binread audio_file_path
audio = { content: audio_file }
response = speech.recognize config: config, audio: audio
results = response.results
results.each_with_index do |result, i|
alternative = result.alternatives.first
puts "-" * 20
puts "First alternative of result #{i}"
puts "Transcript: #{alternative.transcript}"
puts "Channel Tag: #{result.channel_tag}"
end
Nächste Schritte
Informationen zum Suchen und Filtern von Codebeispielen für andere Google Cloud-Produkte finden Sie im Google Cloud-Beispielbrowser.