lightmare/tortoise-tts
1
0
Fork 0
forked from mrq/tortoise-tts
Code Issues 1 Pull Requests Packages Projects Releases Wiki Activity

updates

Browse Source
This commit is contained in:
James Betker 2022-04-25 21:28:18 -06:00
parent cbc7ba0a63
commit 26611b158e
2 changed files with 9 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -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. :) 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 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: produce more realistic outputs then those outside of the training set. Any voice prepended with "train" came from the
atkins, dotrice, grace, harris, kennard, lescault, mol, otto. training set.
### Adding a new voice ### Adding a new voice

10
tortoise_tts.ipynb
View File

@ -52,6 +52,8 @@
"import torch.nn as nn\n", "import torch.nn as nn\n",
"import torch.nn.functional as F\n", "import torch.nn.functional as F\n",
"\n", "\n",
"import IPython\n",
"\n",
"from api import TextToSpeech\n", "from api import TextToSpeech\n",
"from utils.audio import load_audio, get_voices\n", "from utils.audio import load_audio, get_voices\n",
"\n", "\n",
@ -93,7 +95,7 @@
"Had worn them really about the same,\"\"\"\n", "Had worn them really about the same,\"\"\"\n",
"\n", "\n",
"# Pick one of the voices from above\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", "# Pick a \"preset mode\" to determine quality. Options: {\"ultra_fast\", \"fast\" (default), \"standard\", \"high_quality\"}. See docs in api.py\n",
"preset = \"fast\"" "preset = \"fast\""
], ],
@ -115,7 +117,8 @@
" conds.append(c)\n", " conds.append(c)\n",
"\n", "\n",
"gen = tts.tts_with_preset(text, conds, preset)\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": { "metadata": {
"id": "KEXOKjIvn6NW" "id": "KEXOKjIvn6NW"
@ -139,7 +142,8 @@
" conds.append(c)\n", " conds.append(c)\n",
"\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", "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": { "metadata": {
"id": "fYTk8KUezUr5" "id": "fYTk8KUezUr5"