From 26611b158eadf7b273183f575a157b2a6a821fa1 Mon Sep 17 00:00:00 2001
From: James Betker <jbetker@gmail.com>
Date: Mon, 25 Apr 2022 21:28:18 -0600
Subject: [PATCH] updates
---
README.md | 4 ++--
tortoise_tts.ipynb | 10 +++++++---
2 files changed, 9 insertions(+), 5 deletions(-)
diff --git a/README.md b/README.md
index 928d926..0d3a7d4 100644
--- a/README.md
+++ b/README.md
@@ -77,8 +77,8 @@ These reference clips are recordings of a speaker that you provide to guide spee
This repo comes with several pre-packaged voices. You will be familiar with many of them. :)
Most of the provided voices were not found in the training set. Experimentally, it seems that voices from the training set
-produce more realistic outputs then those outside of the training set. The following voices come from the training set:
- atkins, dotrice, grace, harris, kennard, lescault, mol, otto.
+produce more realistic outputs then those outside of the training set. Any voice prepended with "train" came from the
+training set.
### Adding a new voice
diff --git a/tortoise_tts.ipynb b/tortoise_tts.ipynb
index d8b274f..8c38bdb 100644
--- a/tortoise_tts.ipynb
+++ b/tortoise_tts.ipynb
@@ -52,6 +52,8 @@
"import torch.nn as nn\n",
"import torch.nn.functional as F\n",
"\n",
+ "import IPython\n",
+ "\n",
"from api import TextToSpeech\n",
"from utils.audio import load_audio, get_voices\n",
"\n",
@@ -93,7 +95,7 @@
"Had worn them really about the same,\"\"\"\n",
"\n",
"# Pick one of the voices from above\n",
- "voice = 'dotrice'\n",
+ "voice = 'train_dotrice'\n",
"# Pick a \"preset mode\" to determine quality. Options: {\"ultra_fast\", \"fast\" (default), \"standard\", \"high_quality\"}. See docs in api.py\n",
"preset = \"fast\""
],
@@ -115,7 +117,8 @@
" conds.append(c)\n",
"\n",
"gen = tts.tts_with_preset(text, conds, preset)\n",
- "torchaudio.save('generated.wav', gen.squeeze(0).cpu(), 24000)"
+ "torchaudio.save('generated.wav', gen.squeeze(0).cpu(), 24000)\n",
+ "IPython.display.Audio('generated.wav')"
],
"metadata": {
"id": "KEXOKjIvn6NW"
@@ -139,7 +142,8 @@
" conds.append(c)\n",
"\n",
"gen = tts.tts_with_preset(\"They used to say that if man was meant to fly, he’d have wings. But he did fly. He discovered he had to.\", conds, preset)\n",
- "torchaudio.save('captain_kirkard.wav', gen.squeeze(0).cpu(), 24000)"
+ "torchaudio.save('captain_kirkard.wav', gen.squeeze(0).cpu(), 24000)\n",
+ "IPython.display.Audio('captain_kirkard.wav')"
],
"metadata": {
"id": "fYTk8KUezUr5"