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 used the tinygrad whisper implementation as a reference when porting since it's concise. There's no reason the script couldn't be easily modified to only use torch for loading the weights.
May I ask why the need of Tinygrad for the weights conversions? The script seems to be dumping them with np afterwards is read by tinygrad.
The text was updated successfully, but these errors were encountered: