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
Batch inputs in Onsets and Frames to avoid timeouts on longer inputs. #140
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I thiiiiink this is ok? It's super hard to follow what is new code and what got moved
</section> | ||
|
||
<section> |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I know this is super annoying, but can you add a little blurb about what these demos mean? "You can also do the transcription in batches, etc"
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
thank youuuuuuuu, your readers will appreciate it one day!
this.velocityModel.dispose(); | ||
this.activationModel.dispose(); | ||
this.frameModel.dispose(); | ||
this.onsetsCnn.dispose(); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
these names are way better!
music/src/transcription/model.ts
Outdated
}); | ||
} | ||
|
||
/** | ||
* Returns an acoustic stack without setting variables. | ||
*/ | ||
private getAcousticModel(finalActivation: string, hasLstm: boolean) { | ||
const acousticModel = tf.sequential(); | ||
private getacousticCnn() { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nite: getAcousticCnn
(also |
No description provided.