From 1fd91b6437ea01bed9d8321a5827a013052f48ee Mon Sep 17 00:00:00 2001
From: mrq <mrq@ecker.tech>
Date: Fri, 6 Oct 2023 10:13:54 -0500
Subject: [PATCH] cleanup

---
 README.md                 | 11 ++++-------
 scripts/setup-training.sh |  7 +++++++
 scripts/setup.sh          |  5 -----
 3 files changed, 11 insertions(+), 12 deletions(-)
 create mode 100755 scripts/setup-training.sh

diff --git a/README.md b/README.md
index c4e2fc7..097be27 100755
--- a/README.md
+++ b/README.md
@@ -44,12 +44,7 @@ Each model file has a barebones trainer and inference routine.
 
 My pre-trained weights can be acquired from [here](https://huggingface.co/ecker/vall-e).
 
-For example:
-
-```
-git lfs clone --exclude "*.h5" https://huggingface.co/ecker/vall-e ./data/ # remove the '--exclude "*.h5"' if you wish to also download the libre dataset.
-python -m vall_e "The birch canoe slid on the smooth planks." "./path/to/an/utterance.wav" --out-path="./output.wav" yaml="./data/config.yaml"
-```
+A script to setup a proper environment and download the weights can be invoked with `./scripts/setup.sh`
 
 ## Train
 
@@ -60,7 +55,9 @@ Training is very dependent on:
 
 ### Pre-Processed Dataset
 
-A "libre" dataset can be found [here](https://huggingface.co/ecker/vall-e/blob/main/data.h5). Simply place it in the same folder as your `config.yaml`, and ensure its `dataset.use_hdf5` is set to `True`.
+A "libre" dataset can be found [here](https://huggingface.co/ecker/vall-e) under `data.tar.gz`.
+
+A script to setup a proper environment and train can be invoked with `./scripts/setup-training.sh`
 
 ### Leverage Your Own Dataset
 
diff --git a/scripts/setup-training.sh b/scripts/setup-training.sh
new file mode 100755
index 0000000..13a9089
--- /dev/null
+++ b/scripts/setup-training.sh
@@ -0,0 +1,7 @@
+#!/bin/bash
+`dirname $0`/setup.sh
+
+wget -P ./training/valle/ "https://huggingface.co/ecker/vall-e/resolve/main/data.tar.gz"
+wget -P ./training/valle/ "https://huggingface.co/ecker/vall-e/resolve/main/.cache.tar.gz"
+tar -xzf ./training/valle/data.tar.gz -C "./training/valle/" data.h5
+tar -xzf ./training/valle/.cache.tar.gz -C "./training/valle/"
\ No newline at end of file
diff --git a/scripts/setup.sh b/scripts/setup.sh
index 26b6fe0..3f5db75 100755
--- a/scripts/setup.sh
+++ b/scripts/setup.sh
@@ -5,9 +5,4 @@ pip3 install -e .
 
 mkdir -p ./training/valle/ckpt/ar+nar-retnet-8/
 wget -P ./training/valle/ckpt/ar+nar-retnet-8/ "https://huggingface.co/ecker/vall-e/resolve/main/ckpt/ar%2Bnar-retnet-8/fp32.pth"
-wget -P ./training/valle/ "https://huggingface.co/ecker/vall-e/resolve/main/data.tar.gz"
-wget -P ./training/valle/ "https://huggingface.co/ecker/vall-e/resolve/main/.cache.tar.gz"
 wget -P ./training/valle/ "https://huggingface.co/ecker/vall-e/raw/main/config.yaml"
-
-tar -xzf ./training/valle/data.tar.gz -C "./training/valle/" data.h5
-tar -xzf ./training/valle/.cache.tar.gz -C "./training/valle/"
\ No newline at end of file