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

4 ай бұрын

Thanks a lot, really appreciate your nice words! :-) The next part will come soon!

Great video. Looking forward to the custom dataset video.

@martin-thissen

4 ай бұрын

Glad you enjoyed the video! Awesome! :-)

@shashwatrajput6714

8 күн 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.

Hello , thank you for the great tutorial and i wanted to ask when the part2 of this please ?

@martin-thissen

4 ай бұрын

I will upload part 2 probably this weekend! :-)

Nice video Martin! How long did it take you to train the new language?

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

4 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

4 ай бұрын

@@martin-thissen Ahh! yes, got it. Thanks for the clarrification! 😍

Hi Martin, Is it possible to train a voice in the Arabic language and then use that voice to read English text ?

Hello , can i fine tune turtoise for English speech?

heyy , did you implement this without any gpu?

Hi, Great video,Does the TTS work with an RTX2060 ?

@martin-thissen

25 күн бұрын

Unfortunately, 6GB VRAM is probably not enough. :/ You can run it using a free Colab notebook though.

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

2 сағат бұрын

yup, it's stuck

Who's the lucky new owner for the 3080Ti?

Hello. I would like to hear how to create a dataset for your language

Please make a Fine Tune guide for MetaVoice 1B TTS

@martin-thissen

4 ай бұрын

Will look into it! Thanks for the recommendation! :-)

Quite a few subsets in that German language data are of peculiar quality. Anastasia Solokha gave me shievers ))

WHY do you always use someone else's computer, what is the point of this....