mrq/ai-voice-cloning
31
74
Fork 43
Code Issues 223 Pull Requests 5 Packages Projects Releases Wiki Activity

Update Generate

mrq 2023-04-26 04:51:30 +00:00
parent d36c19665a
commit 14f99b7f76
1 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
Generate.md

@ -98,4 +98,13 @@ You can always refer to a list of valid settings under [`./src/utils.py:155`](ht
* `cvvp_amount` * `cvvp_amount`
* `autoregressive_model` * `autoregressive_model`
You can set `autoregressive_model` to `auto` alongside a `voice` to automatically deduce a model for a given voice. You can set `autoregressive_model` to `auto` alongside a `voice` to automatically deduce a model for a given voice.
### Additional Backends
Some additional backends have not-as-tight integration. You can specify a backend by passing `--tts-backend="backend name"` when launching the starting script.
* `vall-e`: Utilizes [mrq/vall-e](https://git.ecker.tech/mrq/vall-e) as the TTS backend
+ Requires the repo to be cloned to `./modules/vall-e/` and installed using `pip3 install -e ./modules/vall-e/`
* `bark`: Utilizes [suno-ai/bark/](https://github.com/suno-ai/bark/) as the TTS backend
+ Requires the repo to be cloned to `./modules/bark/` and installed using `pip3 install -e ./modules/bark/`