Model Scaling, finetuning recipe about lina-speech HOT 10 OPEN

Hey @rishikksh20 ! My bad I uploaded the models but the links expired.
Anyway, everything is on huggingface now ! : https://huggingface.co/lina-speech/all-models/tree/main
There is now a 130M GLA model on librilight medium + one fine tuned on LibriTTS-R. Trained for 300k steps only (clear underfitting)
For the training recipes I'm translating my internal stuff to hf datasets framework and will share this asap, I'll ping you when it's ready.

from lina-speech.

@rishikksh20 I did, it sounds really good. Wonder if they use only SSM or some kind of cross-attention.
Right now I'm still working on a 350M scale up on this dataset you showed me : https://huggingface.co/datasets/parler-tts/mls-eng-10k-tags_tagged_10k_generated

from lina-speech.

Thank you !
I have some questions :

• Have you pretrained from scratch of finetuned a VoiceCraft checkpoint ?
• Have you used MLS or CML-TTS ?

I'm considering scaling up to 130M and further, as soon as I have compute.

from lina-speech.

Hi @theodorblackbird
I am finetuned VoiceCraft over the pre-trained model provided by the author. For multi-lingual data I mixed LibriTTS-r with in-house Hindi data to scale data up to 1k hours then I finetuned 330M model up to 100k and it gave good results.

from lina-speech.

@theodorblackbird
Scaling up to 130M sounds good, Even I can train that small model if I have data module format and training recipe

from lina-speech.

Hows 130M model performing? Saw you update the readme with 130M but not able to grad checkpoint

from lina-speech.

@theodorblackbird Have you checked https://play.cartesia.ai/ , their TTS also based on State Space Model and their samples are amazing. May be they trained Large Model on very large audio dataset.

from lina-speech.

ok, recently Mamba draw lots of attention from Speech domain

from lina-speech.

@theodorblackbird Hi, may I train the TTS model on your own now with this repo? I'd like to run a multi-language version to try it out and see what the sound quality is like on a 44100 sample rate? I'll sync you the results of the experiment then.

from lina-speech.

@rishikksh20 I did, it sounds really good. Wonder if they use only SSM or some kind of cross-attention. Right now I'm still working on a 350M scale up on this dataset you showed me : https://huggingface.co/datasets/parler-tts/mls-eng-10k-tags_tagged_10k_generated

Could you please explain how "audio_token", "align_token", and "text_token" are obtained in the LinaDataModule?

from lina-speech.