audiogen_app.py #185
audiogen_app.py #185
Conversation
|
Hi @cocktailpeanut! Thank you for your pull request and welcome to our community. Action RequiredIn order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at [email protected]. Thanks! |
|
Just signed the contributor license agreement, looking forward to feedback! Also, please let me know if I need to modify anything. One thing I wasn't sure about was whether AudioGen supports Multi Band Diffusion (Looking at the code I kind of assumed it doesn't but maybe I'm wrong), so just took that out of the UI. Let me know if this needs to be supported as well. |
facebook-github-bot
added
the
CLA Signed
|
BTW here's what it looks like in action: https://twitter.com/cocktailpeanut/status/1687565351721005056 |
|
Works for me also, you are amazing @cocktailpeanut |
|
Thanks for your contribution! The MBD model is not available for AudioGen for now and using the one trained on MusicGen may not be optimal. Can you remove the use of MBD from the app ? Another nice addition could be to have text prompt examples to get started similarly to the MusicGen demo, e.g. adding: gr.Examples(
fn=predict_full,
examples=[
[
"Typing on a typewriter",
],
[
"The siren of an emergency vehicle sounds",
],
[
"A duck quacking as birds chirp and a pigeon cooing",
],
[
"Thundering sounds while rain pours",
],
],
inputs=[text],
outputs=[output]
) |
| MODEL = AudioGen.get_pretrained(version) | ||
|
|
||
|
|
||
| def load_diffusion(): |
There was a problem hiding this comment.
We don't have a MultiBandDiffusion model for AudioGen, let's remove this bit from the demo for the merge?
| cfg_coef = gr.Number(label="Classifier Free Guidance", value=3.0, interactive=True) | ||
| with gr.Column(): | ||
| output = gr.Video(label="Generated Audio") | ||
| audio_output = gr.Audio(label="Generated Audio (wav)", type='filepath') |
There was a problem hiding this comment.
Would be great to add some examples as well similarly to the MusicGen demo for users to get some ideas about possible prompts.
A Gradio web UI for the new AudioGen module.
Forked from musicgen_app.py and removed some parts that I think are not relevant for AudioGen.
Confirmed it works.