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
Hi! I've tried different prompts, but the results are very strange. See the following examples:
Precision: fp32. Prompt: "one two three four five six seven eight nine ten." The output is 9 seconds long, but it
only takes the first 3s to read out "eight nine ten", and the other 6s almost contain nothing.
Precision: q4. Prompt: "one two three four five six seven eight nine ten." The output is a 12-second-long murmur
Precision: q4. Prompt: "one two three four five six." The output only reads out "two three four five six".
There are also some issues that occur when using different random seeds or prompts like "[MAN] one two three four five six" and "[happy piano music, playing for ten seconds]".
Are there any solutions or suggestions for setting the prompts accurately (especially for playing music)? Thx!
The text was updated successfully, but these errors were encountered:
bark.cpp is not stable yet in that most prompts still yield non sense. It turns out that there was a bug in the implementation of the 1d convolution that we are solving. Hopefully after this fix, we should have more stable input.
As for the music, we're looking for people to contribute to the repo and accelerate the support of models like Audiocraft.
Hi! I've tried different prompts, but the results are very strange. See the following examples:
only takes the first 3s to read out "eight nine ten", and the other 6s almost contain nothing.
There are also some issues that occur when using different random seeds or prompts like "[MAN] one two three four five six" and "[happy piano music, playing for ten seconds]".
Are there any solutions or suggestions for setting the prompts accurately (especially for playing music)? Thx!
The text was updated successfully, but these errors were encountered: