Es spricht Deutsch | Tortoise TTS Speaking German Demo Clip | Model Download Link in Description
A short demo clip of a German fine-tuned Tortoise TTS model speaking using @ThorstenMueller 's voice dataset
I may post a guide on how it was done, but the process is essentially the same as I went over in past videos.
Thorsten-Voice dataset:
https://github.com/thorstenMueller/Thorsten-Voice
Tortoise model checkpoints and tokenizer here: https://huggingface.co/AOLCDROM/Tortoise-TTS-de
Requires the tokenizer used in training, and code changes to disable text cleaners. At minimum, change english_cleaners to basic_cleaners.
Code changes:
modules\tortoise-tts\tortoise\utils\tokenizer.py
Change Line 201: txt = english_cleaners(txt) and replace it
with txt = basic_cleaners(txt)
modules\tortoise-tts\build\lib\tortoise\utils\tokenizer.py
Change Line 201: txt = english_cleaners(txt) and replace it
with txt = basic_cleaners(txt)
\modules\dlas\dlas\data\audio\paired_voice_audio_dataset.py
Line 133: return text_to_sequence(txt, ['english_cleaners'])
and replace it with: return text_to_sequence(txt, ['basic_cleaners'])
modules\dlas\dlas\data\audio\voice_tokenizer.py
Line 14: from dlas.models.audio.tts.tacotron2.text.cleaners import
english_cleaners
to: from dlas.models.audio.tts.tacotron2.text.cleaners import
english_cleaners, basic_cleaners
Line 85: txt = english_cleaners(txt) to txt =
basic_cleaners(txt)
Line 134: word = english_cleaners(word) to basic_cleaners(word)
Copy and paste German text into the tokenizer tester on the utilities
tab, and you should see it tokenized with all of the special
characters, and no [UNK].
Past Videos:
Tortoise TTS Text Cleaners
https://youtu.be/upNCCaWxxEA
Tortoise TTS Fine-Tuning
https://youtu.be/P3BbCG0hTwU