You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have successfully run the code for the SFT model, but I was wondering how to convert the output into audio. Is this part of the code publicly available?
Thanks!
The text was updated successfully, but these errors were encountered:
Actually, we provide the code for parsing the generated string into the midi file at utils.py and an example in the inference.ipynb. You can check it out.
For the audio part, we use the commercial app ACE to convert the midi file into audio. Other vocal synthesizer apps are also capable of doing that such as synthesizerv.
Hi!
I'm glad you could reply! I've successfully converted the output of the SFT model into a MIDI file and played it. But currently, it generates only pure audio. How can I generate an audio file that plays both the melody and the lyrics together? Is there any code available for this part? Looking forward to your reply.
Thanks!
Hi!
I have successfully run the code for the SFT model, but I was wondering how to convert the output into audio. Is this part of the code publicly available?
Thanks!
The text was updated successfully, but these errors were encountered: