Using speech2text for long duration of audio results in an error with GoogleAPI?

1 回表示 (過去 30 日間)
h612
h612 2019 年 8 月 17 日
編集済み: Raja Palanimurugan 2019 年 8 月 27 日
I'm getting the folloing error when I try to convert speech to text for a longer duration:
'Sync input too long. For audio longer than 1 min use LongRunningRecognize with a ''uri'' parameter.'
I've modified my jason as
{
"key": "abc",
"uri":"https://speech.googleapis.com/v1/speech:longrunningrecognize"
}
But still the error is:
'Sync input too long. For audio longer than 1 min use LongRunningRecognize with a ''uri'' parameter.'
Here is my code:
transcriber = speechClient('Google');
[speech,SampleRate] = audioread('sound_meeting.wav');
text = speech2text(transcriber,speech(:,1),SampleRate,'HTTPTimeOut',25);

回答 (1 件)

Raja Palanimurugan
Raja Palanimurugan 2019 年 8 月 27 日
編集済み: Raja Palanimurugan 2019 年 8 月 27 日
Transcribing long audio signals is not supported by the speech2text function yet. As a workaround, you can split the audio into smaller chunks before sending to speech2text. Hope that helps.

カテゴリ

Help Center および File ExchangeAudio I/O and Waveform Generation についてさらに検索

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by