-
Notifications
You must be signed in to change notification settings - Fork 65
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Transcription from Bytes instead of file #143
Comments
Yes, but the current implementation requires one to provide a path to the file: Line 11 in b763a66
which then just gets read from disk: Line 321 in b763a66
Lines 787 to 806 in b763a66
Since im doing the transcription via a webserver i get the file as a byte array. Which then forces me to actually write those bytes to a file just to have the library read it into memory again making that read & write redundant and skipable |
I see, OK. I will think about how to make the modifications. |
Please use v5.2.5 Example: https://github.com/dongri/openai-api-rs/blob/v5.2.5/examples/audio_transcriptions.rs#L27-L37 |
Describe the feature or improvement you're requesting
I want to create a audio_transcription without having to write the bytes to a file first
Additional context
No response
The text was updated successfully, but these errors were encountered: