seamless_communication
seamless_communication copied to clipboard
Audio is truncated in the output file
I have noticed that when the input audio file exceeds approximately 30 seconds in duration, the resulting output file contains only the first 10 seconds or the last 10 seconds of the audio. This issue affects all functions, including ASR and others. How can I resolve this problem?
Could you share an example audio wav file you encountered this error with?
Test File: Link to the test file
This is a test screenshot. As you can see, it states that it will only use the first one minute but only translates the first approximately 10 seconds of content.
I have also tested it on a local Linux system (WSL2 for Windows 10), and the same issue occurs without displaying an error message.
Hi everyone, I've faced the same issue with audio files longer than 30 s in duration!
Does anyone can answer this issue? thanks.