swiftraccoon/cpp-sdrtrunk-transcriber

Could not extract actual transcription from JSON-like string

Closed this issue · 4 comments

[21:58:10] L66 transcriptionProcessor.cpp Could not extract actual transcription from JSON-like string.
[17:23:44] L66 transcriptionProcessor.cpp Could not extract actual transcription from JSON-like string.

should investigate the cause of this and determine if there's better way of handling whatever error

[15:28:53] transcriptionProcessor.cpp Could not extract actual transcription from JSON-like string. Received transcription string: '{
"error": {
"message": "The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com if you keep seeing this error. (Please include the request ID c309439364681aa8ade64a88967bc227 in your email.)",
"type": "server_error",
"param": null,
"code": null
}
}'
[17:28:07] transcriptionProcessor.cpp Could not extract actual transcription from JSON-like string. Received transcription string: '{"text":""}'

[00:40:52] transcriptionProcessor.cpp Could not extract actual transcription from JSON-like string. Received transcription string: ''

so tl;dr is the bug isn't really a bug, and not a bug within my code AFAICT. just need a better way of handling audio that Whisper doesn't transcribe.

maybe move these mp3s to their own talkgroup folder "Untranscribable" for me/users to experiment and determine why Whisper isn't transcribing

filed enhancement #24 for this