我一直在嘗試使用BlueMix SpeechToText Java庫,尤其是SpeechToText類。IBM沃森語音到文本com.ibm.watson.developer_cloud.speech_to_text.v1內處理大文件
我有很長的WAV文件,我想轉換爲文本。這些文件是〜70MB。目標是使用java API(http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercloud/speech-to-text/api/v1/?java#recognize)來識別文本。我意識到自翻譯結束後,我需要每30秒檢查一次通話狀態,我只需30秒即可檢索最終結果。
爲了做到這一點,而使用REST API,我需要創建一個會話,然後結合我的搜索引擎對所說的對話,這樣我可以查詢在會話中運行的作業的狀態。
我試圖創建一個會話,但會話從不可用。我已經驗證它似乎在提供的webapp(https://stream.watsonplatform.net/speech-to-text/api/v1/sessions?Method=GET)上工作。
此外,我試圖寫我自己的客戶端,我試圖設置從會話中檢索該cookie創建並沒有任何工作。
我也試圖通過安全的WebSockets連接,但無法實現成功連接。
下面是我一直使用的一些示例代碼。
任何想法?
public class Speech2Text extends WatsonService {
private static final Logger logger = LoggerFactory .getLogger(Speech2Text.class);
public static void main(String[] args) throws FileNotFoundException, UnsupportedEncodingException, InterruptedException {
Speech2Text s2t = new Speech2Text();
s2t.httpClient();
// try {
// s2t.webSocketClient();
// } catch (URISyntaxException e) {
// TODO Auto-generated catch block
// e.printStackTrace();
// } catch (IOException e) {
// TODO Auto-generated catch block
// e.printStackTrace();
// }
}
public void httpClient() throws FileNotFoundException,UnsupportedEncodingException {
logger.info("Running http client");
final Stopwatch stopwatch = Stopwatch.createStarted();
SpeechToText service = new SpeechToText();
service.setUsernameAndPassword("XXXXXX","XXXXX");
List<SpeechModel> models = service.getModels();
for (SpeechModel model : models) {
logger.info(model.getName());
}
SpeechSession session = service.createSession("en-US_NarrowbandModel");
System.out.println(session.toString());
SessionStatus status = service.getRecognizeStatus(session);
logger.info(status.getModel());
logger.info(service.getEndPoint());
File audio = new File("/home/baaron/watson-bluemix/answer_06.wav");
Map params = new HashMap();
params.put("audio", audio);
params.put("content_type", "audio/wav");
params.put("continuous", "true");
params.put("session_id", session.getSessionId());
logger.info(service.getEndPoint());
SpeechResults transcript = service.recognize(params);
PrintWriter writer = new PrintWriter("/home/baaron/watson-bluemix/PCCJPApart1test.transcript", "UTF-8");
writer.println(transcript.toString());
SessionStatus status1 = service.getRecognizeStatus(session.getSessionId());
System.out.println(status1);
service.deleteSession(session.getSessionId());
writer.close();
stopwatch.stop();
logger.info("Processing took: " + stopwatch + ".");
}
public void webSocketClient() throws URISyntaxException, IOException,
InterruptedException {
logger.info("Running web socket client");
String encoding = new String(Base64.encodeBase64String("XXXXXXXXXX".getBytes()));
HttpPost httppost = new HttpPost( "https://stream.watsonplatform.net/authorization/api/v1/token?url=https://stream.watsonplatform.net/speech-to-text/api");
httppost.setHeader("Authorization", "Basic " + encoding);
System.out.println("executing request " + httppost.getRequestLine());
DefaultHttpClient httpclient = new DefaultHttpClient();
HttpResponse response = httpclient.execute(httppost);
HttpEntity entity = response.getEntity();
logger.info(response.getStatusLine().getReasonPhrase());
WebSocketImpl.DEBUG = true;
BufferedReader reader = new BufferedReader(new InputStreamReader( entity.getContent()));
StringBuilder out = new StringBuilder();
String line;
while ((line = reader.readLine()) != null) {
out.append(line);
}
String token = out.toString();
final WebSocketClient client = new WebSocketClient(
new URI("wss://stream.watsonplatform.net/speech-to-text-beta/api/v1/recognize?watson-token=" + token)) {
@Override
public void onMessage(String message) {
JSONObject obj = new JSONObject(message);
// String channel = obj.getString("channel");
}
@Override
public void onOpen(ServerHandshake handshake) {
System.out.println("opened connection");
}
@Override
public void onClose(int code, String reason, boolean remote) {
System.out.println("closed connection");
}
@Override
public void onError(Exception ex) {
ex.printStackTrace();
}
};
// open websocket
SSLContext sslContext = null;
try {
sslContext = SSLContext.getInstance("TLS");
sslContext.init(null, null, null);
} catch (NoSuchAlgorithmException e) {
e.printStackTrace();
} catch (KeyManagementException e) {
e.printStackTrace();
}
client.setWebSocketFactory(new DefaultSSLWebSocketClientFactory(
sslContext));
logger.info("CONNECTED: " + client.connectBlocking());
JSONObject obj = new JSONObject();
obj.put("action", "start");
obj.put("content-type", "audio/wav");
client.send(obj.toString());
logger.info("Done");
}
}
看看這個答案http://stackoverflow.com/questions/36504879/watson-stt-java-varying-results-between-websockets -java-和HTTP-POST/36806207#36806207 –