Troubleshooting of Google cloud speech to text: Difference between revisions

Jump to navigation Jump to search
m
 
(13 intermediate revisions by the same user not shown)
Line 1: Line 1:
{{Template:Speech to text}}


Troubleshooting of Google [https://cloud.google.com/speech-to-text/ Cloud Speech-to-Text - 語音辨識]
Troubleshooting of Google [https://cloud.google.com/speech-to-text/ Cloud Speech-to-Text - 語音辨識]
== Brief instruction ==
* If the audio file's duration is '''longer''' than 1 minute, (1) Use the uri: {{kbd | key=<nowiki>speech:longrunningrecognize</nowiki>}} NOT {{kbd | key=<nowiki>speech:recognize</nowiki>}} (2) Upload files to [https://console.cloud.google.com/storage/ Google cloud storage] (gcs)
* If the audio file's duration is '''shorter''' than 1 minute, (1) Use the uri: {{kbd | key=<nowiki>speech:longrunningrecognize</nowiki>}}. Or choose to use {{kbd | key=<nowiki>speech:recognize</nowiki>}} (2) Use the files are located on the computer. Or choose to upload files to [https://console.cloud.google.com/storage/ Google cloud storage] (gcs)


== ERROR: (gcloud.auth.application-default.print-access-token) The Application Default Credentials are not available ==
== ERROR: (gcloud.auth.application-default.print-access-token) The Application Default Credentials are not available ==
Line 9: Line 14:
</pre>
</pre>


Solution<ref>[https://cloud.google.com/docs/authentication/production Setting Up Authentication for Server to Server Production Applications  |  Authentication  |  Google Cloud]</ref><ref>[https://cloud.google.com/speech-to-text/docs/quickstart-protocol Quickstart: Using the Command Line  |  Cloud Speech API Documentation  |  Google Cloud]</ref>: Key-in the following command. And then the browser will be opened automatically.
Solution<ref>[https://cloud.google.com/docs/authentication/production Setting Up Authentication for Server to Server Production Applications  |  Authentication  |  Google Cloud]</ref><ref>[https://cloud.google.com/speech-to-text/docs/quickstart-protocol Quickstart: Using the Command Line  |  Cloud Speech API Documentation  |  Google Cloud]</ref>: Key-in the following command. And then the browser will be opened automatically. Follow the steps on the web page.
<pre>
<pre>
$ gcloud auth application-default login
$ gcloud auth application-default login
</pre>
</pre>


== Invalid audio channel count ==
== Invalid audio channel count ==
Line 41: Line 45:
</pre>
</pre>


Solution: Specify the encoding of audio file. For details, see [https://cloud.google.com/speech-to-text/docs/encoding Introduction to Audio Encoding  |  Cloud Speech-to-Text API  |  Google Cloud] & [https://cloud.google.com/speech-to-text/docs/reference/rest/v1/RecognitionConfig#AudioEncoding RecognitionConfig  |  Cloud Speech-to-Text API  |  Google Cloud]. You may use VLC player to view the encoding of audio file<ref>[https://forum.videolan.org/viewtopic.php?t=95136#p315198 How to view audio bitrate in VLC - The VideoLAN Forums]</ref>. If the codec (encoding) of audio file is not in the allowed list on [https://cloud.google.com/speech-to-text/docs/reference/rest/v1/RecognitionConfig#AudioEncoding page], the codec (encoding) of audio file should be converted.
Solution: Specify the encoding of audio file. For details, see [https://cloud.google.com/speech-to-text/docs/encoding Introduction to Audio Encoding  |  Cloud Speech-to-Text API  |  Google Cloud] & [https://cloud.google.com/speech-to-text/docs/reference/rest/v1/RecognitionConfig#AudioEncoding RecognitionConfig  |  Cloud Speech-to-Text API  |  Google Cloud]. You may use VLC player to view the encoding of audio file<ref>[https://forum.videolan.org/viewtopic.php?t=95136#p315198 How to view audio bitrate in VLC - The VideoLAN Forums]</ref>. If the codec (encoding) of audio file is not in the allowed list on [https://cloud.google.com/speech-to-text/docs/reference/rest/v1/RecognitionConfig#AudioEncoding page], the codec (encoding) of audio file should be converted by [[Audio converter | audio converter]].


== For audio longer than 1 min use LongRunningRecognize with a 'uri' parameter ==
== If the audio file's duration is longer than 1 minute use LongRunningRecognize with a 'uri' parameter ==
input
input
<pre>
<pre>
Line 80: Line 84:
</pre>
</pre>


Solution: (1) Use the short audio file which shorter than 1 min or (2) Modify the uri from {{kbd | key=<nowiki>speech:recognize</nowiki>}} to {{kbd | key=<nowiki>speech:longrunningrecognize</nowiki>}} for long audio file which longer than 1 min
Solution: (1) If the audio file's duration is shorter than 1 min, use the uri: {{kbd | key=<nowiki>speech:recognize</nowiki>}}. (2) If the audio file's duration is longer than 1 min. Upload files to [https://console.cloud.google.com/storage/ Google cloud storage] (gcs). Modify the uri from {{kbd | key=<nowiki>speech:recognize</nowiki>}} to {{kbd | key=<nowiki>speech:longrunningrecognize</nowiki>}}.
<pre>
<pre>
$ curl -s -H "Content-Type: application/json" \
$ curl -s -H "Content-Type: application/json" \
Line 103: Line 107:


Solution: (1) Use the short audio file which shorter than 1 min or (2) Modify the uri from {{kbd | key=<nowiki>speech:recognize</nowiki>}} to {{kbd | key=<nowiki>speech:longrunningrecognize</nowiki>}} for long audio file which longer than 1 min
Solution: (1) Use the short audio file which shorter than 1 min or (2) Modify the uri from {{kbd | key=<nowiki>speech:recognize</nowiki>}} to {{kbd | key=<nowiki>speech:longrunningrecognize</nowiki>}} for long audio file which longer than 1 min


== sample_rate_hertz (16000) in RecognitionConfig must either be unspecified or match the value in the FLAC header ==
== sample_rate_hertz (16000) in RecognitionConfig must either be unspecified or match the value in the FLAC header ==
Line 154: Line 157:
Solution: modify the uri from {{kbd | key=<nowiki>https://speech.googleapis.com/v1/speech:longrunningrecognize</nowiki>}} to {{kbd | key=<nowiki>https://speech.googleapis.com/v1p1beta1/speech:longrunningrecognize</nowiki>}}
Solution: modify the uri from {{kbd | key=<nowiki>https://speech.googleapis.com/v1/speech:longrunningrecognize</nowiki>}} to {{kbd | key=<nowiki>https://speech.googleapis.com/v1p1beta1/speech:longrunningrecognize</nowiki>}}


== Related forum ==
== Related ==
 
* {{Gd}} [https://cloud.google.com/speech-to-text/docs/best-practices Best Practices  |  Cloud Speech API Documentation  |  Google Cloud]
* official document: [https://cloud.google.com/speech-to-text/docs/troubleshooting Troubleshooting of Google Speech-to-text API]
* [https://groups.google.com/forum/#!forum/cloud-speech-discuss cloud-speech-discuss - Google Group]
* [https://groups.google.com/forum/#!forum/cloud-speech-discuss cloud-speech-discuss - Google Group]
* [https://github.com/GoogleCloudPlatform/php-docs-samples/tree/master/speech/ php-docs-samples/speech at master · GoogleCloudPlatform/php-docs-samples]
* [[Text to speech]]


== References ==
== References ==
Line 163: Line 171:
{{Template:Troubleshooting}}
{{Template:Troubleshooting}}


[[Category:Google]]
[[Category:Google]] [[Category:NLP]] [[Category:Tool]]
Anonymous user

Navigation menu