README.md

metadata

license: agpl-3.0

This repo catalogs my weights for use with my VALL-E implementation as I try and iron out the kinks.

The model currently is in a semi-usable state, and I'm releasing them now in hopes that it also helps jumpstart anyone else that wants to use them.

To reiterate, this is by no means complete. I am not passing this off as competitive.

Models

• config.retnet.yaml / ar+nar-retnet-8: The previously released weights.

  • This configuration utilizes a RetNet (retention based transformer) as the underlying architecture due to a number of misleading interpretations with comparisons, for better or for worse.
    • Prompt and response embeddings are summed (further RVQ levels gets the previous RVQ levels' embeddings factored in).
    • Tokenizer is a homebrewed "naive" implementation.
  • This model received the most training time between my 4070Ti, 7900XTX, and a few rental rigs to training further progress, entirely at bfloat16 with prodigyopt (and a few optimizer restarts).
  • The later part of training aimed to shuffle between speakers rather than the global pool of utterances to better focus on zero-shot performance. Due to this, I feel it achieved decent zero-shot performance.
  • However, due to the dataset being aggressively trimmed under 12 seconds for memory savings during training, it suffers trying to inference non-short utterances. Additional training may fix this, the following models seemed to adapt well to longer utterances.
  • Prior testing showed that longer prompt durations results in better utterances.

• config.llama.yaml / ar+nar-llama-8: The most recent-ishly trained weights after learning from my mistakes.

  • This configuration utilizes Llama's attention-based transformer as the underlying architecture, making use of creature comforts like RoPE, GQA, and memory-efficient attention (trained under xformers, shouldn't really affect things).
    • Prompt and response embeddings are NOT summed (each RVQ level only attends to the current RVQ level).
    • Utilizes a HF tokenizer for "optimal" vocab.
    • The current RVQ level is included as a token as well to help guide NAR tasks better.
  • This model received a few days of training on my 4xV100s, stepping up the duration window to try and better make the model inference for longer utterances.
    • Some sessions end up training the current duration window for a few epochs, but I don't know how much it affected things.
  • However, it seems to only do well with long utterances. Short utterances fumble. I believe further training with a variety of durations should allow the AR to handle a variety of durations.
    • I believe the "slowly stepping up the context length" only works for text, and not audio.
  • Zero-shot performance leaves a bit to be desired, as it did not receive the special training prioritizing shuffling between speakers rather than the global pool of utterances.
  • Testing showed that, despite also stepping up the prompt duration, it really likes three second prompts.
  • Definitely needs additional training.

• config.llama.split.yaml / ar-llama-1 + nar-llama-8: The above model, but split and trained a little bit more.

  • This experiment is to see whether the AR and NAR benefitted from being split up after enough pretraining, to un-"lobotomize" any penalties from attending to two different tasks (as the AR predicts the next token, and the NAR predicts the same token but a different level).
  • I believe I trained each separate model an additional extra day for another additional audio-duration window for similar training lengths.
  • I don't think audio quality differs a non-trivial amount to warrant splitting the model.

There's a bunch of additional configurations (between the underlying arch, embedding modes, interleaving, and even a NAR-"only" model) that are to be further explored, but current experiments showed they either are not worth the additional performance penalties (interleaving) or fall flat (NAR-"only", chunked interleaving).