-
https://git.ecker.tech/ aims to provide a place to share my efforts while maintaining true ownership of my code, as I do not trust GitHub.
XMR: 4B9TQdkAkBFYrbj5ztvTx89e5LpucPeTSPzemCihdDi9EBnx7btn8RDNZTBz2zihWsjMnDkzn5As1LU6gLv3KQy8BLsZ8SG
- Joined on
2022-10-10
4744120be2
added VALL-E inference support (very rudimentary, gimped, but it will load a model trained on a config generated through the web UI)
653d0b761d
Make it able to work with also passing --yaml (necessary to inference from outside of CLI, as the config is loaded on initialization)
108fda9c5c
cleaned up some things (made inferencing wrapped in a class, able to load models into memory without needing to export, but requires deepspeed still)
Added ability to mix models in commit f66281f10cb952706fa97669d8d8c37cb7a261c1. I might need to actually lift Voldy's Web UI's implementation and have a third model and do three-way-merging just…
There's one last thing that I keep forgetting to try and implement myself to see how the results are. I only remembered it earlier for VALL-E uses, but I don't see why it wouldn't also work for…
I'm so mad. I had a decently lengthed followup, but because I used a stupid emoji that the text entry field suggested, it ate it all up.
Pah, oh well. It was mostly outlining a path I should…
What would such a dataset entail?
Not too sure. It'd probably be a mix between:
- some already open speech collections.
- samples of decent quality from the list of sample collections I…
I've had outstanding results with WhisperX once I started running it with --align_model WAV2VEC2_ASR_LARGE_LV60K_960H. The downside is that it doesn't support many languages out of the box (but…
Yeah, a fresh install with fresh settings will take ages on the initial run. All these things will definitely eat up time:
- download several models (the AR, the diffusion, the CLVP, the…
Oh right, I forgot to actually test an English-but-varied speaker finetune to see how well it'd work for zero shot. desu it hasn't been something I'd care all that much to see (partially because I…
Unfortunately it's a deep seated Gradio regression, there's not much I can do about it: mrq/ai-voice-cloning#116.
I couldn't consistently replicate it, but I would…
The japanese tortoise model is really cool. Would VALL-E X provide better results?
Hard to say.
I feel whatever base VALL-E puts out for Japanese is an indicator of how well VALL-E X will…