Voice Cloning For Any Language | Fine-Tuning Tortoise-TTS | Part 1

  Рет қаралды 7,462

Martin Thissen

Martin Thissen

Күн бұрын

Пікірлер: 29
@carlosedubarreto
@carlosedubarreto 9 ай бұрын
Wow. incredible. I was trying to make a Tortoise TTS to work in portuguese and was lost, now I have a way to do that, thanks for sharing this info. Now I just have to wait for the other parts, and find free time to do that. that is an amazing effort from your side, since its a very complex topic 👏👏 Congrats;
@martin-thissen
@martin-thissen 9 ай бұрын
Thanks a lot, really appreciate your nice words! :-) The next part will come soon!
@bouchrasaidi1174
@bouchrasaidi1174 9 ай бұрын
Hello , thank you for the great tutorial and i wanted to ask when the part2 of this please ?
@martin-thissen
@martin-thissen 9 ай бұрын
I will upload part 2 probably this weekend! :-)
@olcaybuyan
@olcaybuyan 9 ай бұрын
Great video. Looking forward to the custom dataset video.
@martin-thissen
@martin-thissen 9 ай бұрын
Glad you enjoyed the video! Awesome! :-)
@shashwatrajput6714
@shashwatrajput6714 5 ай бұрын
@@martin-thissen Hey, I am still waiting on that video? Hahaha.. I wanna clone Elon Musk's voice and I have 3 hours of recorded audio of him as well I gathered it from podcasts. Need your help.
@dogfoxpodcast
@dogfoxpodcast 2 ай бұрын
Hi. Great job. I'm encountering the same problem over and over, though: ModuleNotFoundError: No module named 'unified_voice2'. Any idea of why this happens?
@awnyfaris9326
@awnyfaris9326 8 ай бұрын
Hi Martin, Is it possible to train a voice in the Arabic language and then use that voice to read English text ?
@shovonjamali7854
@shovonjamali7854 9 ай бұрын
Another great one, really useful but I have a question though. The dataset you used, has different speakers (like maybe even male or female too), right? So, for training the model, we can put all the wavs from different speakers under a single wavs folder, we don't need to create/manage different ones for different speakers, is my understanding correct?
@martin-thissen
@martin-thissen 9 ай бұрын
Thanks a lot! Yes, your understanding is correct! If you wanted, you could however keep the wavs in separated folders for each speaker. You just need to make sure that paths stated in the train.txt and val.txt files is correct for all files.
@shovonjamali7854
@shovonjamali7854 9 ай бұрын
@@martin-thissen Ahh! yes, got it. Thanks for the clarrification! 😍
@albertigle
@albertigle 5 ай бұрын
Nice video Martin! How long did it take you to train the new language?
@tempertephra
@tempertephra Ай бұрын
I used files from your fork with audiobook maker fro jarod mica. Quite passable but longer sentences corrupt.
@FAITHseek
@FAITHseek 9 ай бұрын
Please make a Fine Tune guide for MetaVoice 1B TTS
@martin-thissen
@martin-thissen 9 ай бұрын
Will look into it! Thanks for the recommendation! :-)
@BoskaPalma
@BoskaPalma 4 ай бұрын
My transcription txt file is around 1GB, i am running tokenizer now for about 30 minutes and don't see any progress 🤔 Running locally on m1 max mac studio
@BoskaPalma
@BoskaPalma 4 ай бұрын
yup, it's stuck
@chiyanchandru5914
@chiyanchandru5914 3 ай бұрын
how can i run this code local machine ?
@bouchrasaidi1174
@bouchrasaidi1174 8 ай бұрын
Hello , can i fine tune turtoise for English speech?
@MightyMindsDev
@MightyMindsDev 7 ай бұрын
Hello. I would like to hear how to create a dataset for your language
@ashuu9257
@ashuu9257 9 ай бұрын
heyy , did you implement this without any gpu?
@Athelstanovsky
@Athelstanovsky 5 ай бұрын
Hi, Great video,Does the TTS work with an RTX2060 ?
@martin-thissen
@martin-thissen 5 ай бұрын
Unfortunately, 6GB VRAM is probably not enough. :/ You can run it using a free Colab notebook though.
@bobsmithy3103
@bobsmithy3103 8 ай бұрын
Who's the lucky new owner for the 3080Ti?
@DM-dy6vn
@DM-dy6vn 8 ай бұрын
Quite a few subsets in that German language data are of peculiar quality. Anastasia Solokha gave me shievers ))
@timothymaggenti717
@timothymaggenti717 5 ай бұрын
WHY do you always use someone else's computer, what is the point of this....
@miwoj
@miwoj 2 ай бұрын
WHERE IS THE PART WHERE YOU SHOW US HOW IT CAME OUT ?? WE WOULD REALLLY LIKE TO HEAR IF RESULT IS WORTH ALL THAT EFFORT OR IF WORKS AT ALL. dislike for being useless and wasting my time.
Tortoise-TTS Fully Explained | Part 1 | Architecture Design
19:32
Martin Thissen
Рет қаралды 2,3 М.
How I Built My $10,000 Deep Learning Workstation
22:25
Martin Thissen
Рет қаралды 15 М.
It works #beatbox #tiktok
00:34
BeatboxJCOP
Рет қаралды 41 МЛН
Мясо вегана? 🧐 @Whatthefshow
01:01
История одного вокалиста
Рет қаралды 7 МЛН
Сестра обхитрила!
00:17
Victoria Portfolio
Рет қаралды 958 М.
Voice Cloning For Any Language | Fine-Tuning Tortoise-TTS | Part 2
11:59
Legion Retreat 2024 - Legate and cuPyNumeric - Wonchan Lee
28:10
Legion Programming System
Рет қаралды 14
World’s Fastest Talking AI: Deepgram + Groq
11:45
Greg Kamradt
Рет қаралды 57 М.
Text to Speech Fine-tuning Tutorial
1:15:44
Trelis Research
Рет қаралды 8 М.
LLaMA2 for Multilingual Fine Tuning?
15:59
Sam Witteveen
Рет қаралды 16 М.
How to Clone Most Languages Using Tortoise TTS - AI Voice Cloning
29:40
Free Speech: Reviewing Coqui-ai, Mycroft Mimic3 and Tortoise TTS Libraries
14:23
I think I figured how to clone (almost) any language in Tortoise TTS
10:45
It works #beatbox #tiktok
00:34
BeatboxJCOP
Рет қаралды 41 МЛН