Discussions

• 2 You must be logged in to vote

  🙏

  Speech Continuation Task

  radhavishnu asked Nov 18, 2023 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  💬

  How does the soundstream work after training?

  DingWeiPeng started Nov 13, 2023 in General

  

  

  0
• 1 You must be logged in to vote

  💬

  Sanity Check for Semantic Transformer during inference - does inference finish?

  rgxb2807 started Nov 7, 2023 in General · Closed

  

  

  1
• 2 You must be logged in to vote

  🙏

  Some problems with coarse transformer training

  dwangF0 asked Oct 11, 2023 in Q&A · Unanswered

  

  

  0
• 2 You must be logged in to vote

  🙏

  Is it a typo?

  dwangF0 asked Sep 23, 2023 in Q&A · Closed · Unanswered

  

  

  2
• 2 You must be logged in to vote

  🙏

  Has anyone made it to train a working FineTransformer?

  cyanbx asked Mar 1, 2023 in Q&A · Unanswered

  

  

  

  

  44
• 1 You must be logged in to vote

  💬

  semantic training

  hyhzl started Aug 1, 2023 in General

  

  

  

  

  7
• 2 You must be logged in to vote

  💬

  Save/load from checkpoints leading to strange loss shifts

  LWprogramming started Jul 28, 2023 in General · Closed

  

  

  7
• 1 You must be logged in to vote

  🙏

  SemanticTransformer training

  amitaie asked Jun 26, 2023 in Q&A · Unanswered

  

  

  

  

  15
• 9 You must be logged in to vote

  💡

  Choice of semantic tokens

  eonglints started Nov 7, 2022 in Ideas

  

  

  

  

  30
• 2 You must be logged in to vote

  🙏

  Asking for some SoundStream training info

  amitaie asked Feb 22, 2023 in Q&A · Unanswered

  

  

  

  

  95
• 2 You must be logged in to vote

  💡

  Concatenation vs. addition of acoustic token quantizer dimension

  mxkrn started Apr 19, 2023 in Ideas

  

  

  

  

  18
• 1 You must be logged in to vote

  💬

  How to train 3 transformers at the same time

  jidanhuang started May 7, 2023 in General · Closed

  

  

  0
• 1 You must be logged in to vote

  🙏

  Training curves for discriminator losses?

  turian asked Apr 28, 2023 in Q&A · Unanswered

  

  

  1
• 3 You must be logged in to vote

  💡

  Potentially useful pretrained models

  gkucsko started Apr 19, 2023 in Ideas

  

  

  

  

  7
• 1 You must be logged in to vote

  🙏

  Questions about cross attention without encoder

  kn asked Apr 23, 2023 in Q&A · Closed · Unanswered

  

  

  1
• 3 You must be logged in to vote

  🙏

  what do researchers think about natural speech 2?

  lucidrains asked Apr 20, 2023 in Q&A · Unanswered

  

  

  1
• 1 You must be logged in to vote

  🙏

  natural speech 2

  lucidrains asked Apr 20, 2023 in Q&A · Closed · Unanswered

  

  

  0
• 2 You must be logged in to vote

  💬

  Is it possible to train audiolm with lyra v2?

  seastar105 started Apr 2, 2023 in General

  

  

  0
• 1 You must be logged in to vote

  🙏

  SoundStream overfitting

  Dannynis asked Mar 5, 2023 in Q&A · Unanswered

  

  

  

  

  3
• 2 You must be logged in to vote

  🙏

  Has anyone trained a good sounding SoundStream model on music?

  vican9000 asked Mar 29, 2023 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  🙏

  Attention in the SoundStream model

  amitaie asked Mar 22, 2023 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  💬

  FineTransformer Trainning with Multi-GPU using codec from Encodec

  Liujingxiu23 started Mar 17, 2023 in General

  

  

  0
• 1 You must be logged in to vote

  💬

  How to generate speech continuation while keeping the speaker unchanged？

  lzl1456 started Mar 21, 2023 in General · Closed

  

  

  0
• 2 You must be logged in to vote

  🙏

  SoundStream codebook dim

  amitaie asked Mar 2, 2023 in Q&A · Unanswered

  

  

  0