I have faced this issue more than once, am trying to transcribe an audio file which involves data regarding palesting, and I just keep getting this error
ERROR {
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 e93cecad4baeee......................... in your email.)',
type: 'server_error',
param: null,
code: null
}
}
is Whisper forbidding requests related to or talking about palestine somehow ?
Try to use the free whisper python module instead, if you can. I think it is now updated to version 3, better than the API, which is still using whisper-1.
well, the issue is why it’s not being transcribed, I have contacted OpenAI, they said nothing should be stopping it from being generated, but, this doesn’t seem to be the case
In English, I went over to Al Jazeera and read a news story to the completion playground’s Whisper. While it didn’t piece my attempts at pronouncing names back into correct spelling, no errors.
The API playground, under “completions” (such as for “instruct” AI model), has a TTS microphone. You can just read to it as I did to my PC’s built-in microphone (and get billed for seconds of whisper).