vall-e/README.md

<p align="center">
<img src="./vall-e.png" width="500px"></img>
</p>

# VALL'E

An unofficial PyTorch implementation of [VALL-E](https://vall-e-demo.ecker.tech/) (last updated: `2024.12.11`), utilizing the [EnCodec](https://github.com/facebookresearch/encodec) encoder/decoder.

A demo is available on HuggingFace [here](https://huggingface.co/spaces/ecker/vall-e).

## Requirements

Besides a working PyTorch environment, the only hard requirement is [`espeak-ng`](https://github.com/espeak-ng/espeak-ng/) for phonemizing text:
- Linux users can consult their package managers on installing `espeak`/`espeak-ng`.
- Windows users are required to install [`espeak-ng`](https://github.com/espeak-ng/espeak-ng/releases/tag/1.51#Assets).
  + additionally, you may be required to set the `PHONEMIZER_ESPEAK_LIBRARY` environment variable to specify the path to `libespeak-ng.dll`.
- In the future, an internal homebrew to replace this would be fantastic.

## Install

Simply run `pip install git+https://git.ecker.tech/mrq/vall-e` or `pip install git+https://github.com/e-c-k-e-r/vall-e`.

This repo is tested under Python versions `3.10.9`, `3.11.3`, and `3.12.3`.

## Pre-Trained Model

Pre-trained weights can be acquired from
* [here](https://huggingface.co/ecker/vall-e) or automatically when either inferencing or running the web UI.
* `./scripts/setup.sh`, a script to setup a proper environment and download the weights. This will also automatically create a `venv`.
* when inferencing, either through the web UI or CLI, if no model is passed, the default model will download automatically instead, and should automatically update.

## Documentation

The provided documentation under [./docs/](./docs/) should provide thorough coverage over most, if not all, of this project.

Markdown files should correspond directly to their respective file or folder under `./vall_e/`.
Rewrite init 2023-08-02 21:53:35 +00:00			`<p align="center">`
			`<img src="./vall-e.png" width="500px"></img>`
			`</p>`

god I am inexperienced with retaining compat from previous weights, I hope no one actually has weights 2023-08-19 02:29:20 +00:00			`# VALL'E`
Rewrite init 2023-08-02 21:53:35 +00:00
more fixes for local engine backend 2024-12-12 20:38:42 +00:00			An unofficial PyTorch implementation of [VALL-E](https://vall-e-demo.ecker.tech/) (last updated: `2024.12.11`), utilizing the [EnCodec](https://github.com/facebookresearch/encodec) encoder/decoder.
fixed training stats not loading from exported weights, a bit of a readme cleanup, updated example training yaml 2023-09-24 00:59:00 +00:00
agony 2024-11-06 04:30:49 +00:00			`A demo is available on HuggingFace [here](https://huggingface.co/spaces/ecker/vall-e).`

god I am inexperienced with retaining compat from previous weights, I hope no one actually has weights 2023-08-19 02:29:20 +00:00			`## Requirements`
Rewrite init 2023-08-02 21:53:35 +00:00
readme tweaks 2024-06-29 02:02:54 +00:00			Besides a working PyTorch environment, the only hard requirement is [`espeak-ng`](https://github.com/espeak-ng/espeak-ng/) for phonemizing text:
finally got around to removing omegaconf 2024-06-08 01:23:53 +00:00			- Linux users can consult their package managers on installing `espeak`/`espeak-ng`.
			- Windows users are required to install [`espeak-ng`](https://github.com/espeak-ng/espeak-ng/releases/tag/1.51#Assets).
			+ additionally, you may be required to set the `PHONEMIZER_ESPEAK_LIBRARY` environment variable to specify the path to `libespeak-ng.dll`.
readme tweaks, set the (unused) default model download URL back to the base ar+nar-llama-8 model, as ar+nar-tts+stt-llama-8 was renamed back to it since it performs well 2024-10-06 03:53:53 +00:00			`- In the future, an internal homebrew to replace this would be fantastic.`
Rewrite init 2023-08-02 21:53:35 +00:00
god I am inexperienced with retaining compat from previous weights, I hope no one actually has weights 2023-08-19 02:29:20 +00:00			`## Install`
Rewrite init 2023-08-02 21:53:35 +00:00
deprecate sole AR/NAR model by only keeping the AR+NAR (the beauty of no one using this is that I can break compat as much as I want), add tone token for when I classify my dataset with tone/emotion in the future, some other things 2024-04-16 00:54:32 +00:00			Simply run `pip install git+https://git.ecker.tech/mrq/vall-e` or `pip install git+https://github.com/e-c-k-e-r/vall-e`.
Rewrite init 2023-08-02 21:53:35 +00:00
rolling context finally (use last N utterances as the prefix for the next gen), option to split input text prompt by sentences instead of lines (or no splitting) 2024-12-05 02:31:44 +00:00			This repo is tested under Python versions `3.10.9`, `3.11.3`, and `3.12.3`.
ops 2023-08-04 01:36:19 +00:00
added repo with my weights so far 2023-08-22 18:09:44 +00:00			`## Pre-Trained Model`

rolling context finally (use last N utterances as the prefix for the next gen), option to split input text prompt by sentences instead of lines (or no splitting) 2024-12-05 02:31:44 +00:00			`Pre-trained weights can be acquired from`
			`* [here](https://huggingface.co/ecker/vall-e) or automatically when either inferencing or running the web UI.`
			* `./scripts/setup.sh`, a script to setup a proper environment and download the weights. This will also automatically create a `venv`.
			`* when inferencing, either through the web UI or CLI, if no model is passed, the default model will download automatically instead, and should automatically update.`
added repo with my weights so far 2023-08-22 18:09:44 +00:00
documentation under ./docs/ 2024-11-05 22:11:01 +00:00			`## Documentation`
Rewrite init 2023-08-02 21:53:35 +00:00
documentation under ./docs/ 2024-11-05 22:11:01 +00:00			`The provided documentation under [./docs/](./docs/) should provide thorough coverage over most, if not all, of this project.`
Rewrite init 2023-08-02 21:53:35 +00:00
documentation under ./docs/ 2024-11-05 22:11:01 +00:00			Markdown files should correspond directly to their respective file or folder under `./vall_e/`.