snac

snac copied to clipboard

Hello, thank you for sharing this nice work Have you tried using shared codebook just like the method used in [VAR](https://github.com/FoundationVision/VAR) And here is the discussion about the codebook in...

BakerBunker

Hi, thanks a lot for the great work, the use of tokens with different resolutions is in line with the intuitive understanding of the audio signal (like a representation of...

jiaweiru

Architectural questions (SNAC vs Vocos)

2

Hello, why did you switch back to building on DAC-style waveform outputs for SNAC after showing it's possible to completely get rid of aliasing by generating complex spectrograms with Vocos?...

zaptrem

Would you mind sharing the SNAC training code? :)

christophschuhmann

what is the codebook size/vocab size?

1

what is the codebook size / vocab size for encoded snac data for the various models?

huu4ontocord

Hi, when i see the config on hugging face for model predict, the attn_window_size is null, so i wonder if the attention is used in training state? And, can you...

Naminwang

Is there a blog or paper out there that compare SNAC with other Neural Audio Codecs (DAC, SoundStream, Encodec, etc...) in terms of quality and efficiency ?

MohamedAliRashad

Hello, thanks for your excellent work. When I tried to train SNAC model by DAC training procedure, my codebook loss cracked sometimes. Therefore, my reconstruction loss cracked sometimes during training...

haitran61

Has SNAC been trained using Chinese corpus? 请问SNAC使用中文语料训练过吗？

spectaclecs

Is this could be used for audio synthesis?

2

For instance, LLM out produce snac tokens, and decode into audio?

MonolithFoundation