Tortoise17

Since the paper has been published, is there any chance to get the Audio LDM2 checkpoints for training or its dataset model and training pipeline for speech model??

I have trained an additional language other than English with almost 10,000 hours. Still when I use it to produce the audio voice, there are strange voices at the end...

Multi-gpu option is possible?

2

I want to ask if there is possibility to use the multi-gpus . I tried to enter 0,1 and the option didn't work for the training GUI. If anyone can...

This is really a great effort and help.

Using the random voice option changes voice after two sentences. Is there any way to fix this issue and get the random voice at least for complete input paragraph or...

I have trained an additional language other than English with almost 10,000 hours. Still when I use it to produce the audio voice, there are strange voices at the end...

Dear Friends, I want to ask that if we have audio data, is it possible to prepare GIGASpeech format in any other language? If you could guide.??

Turing architecture error on Nvidia Quadro T1000

2

I am facing this error RuntimeError: FlashAttention only supports Ampere GPUs or newer. while architecture is Turing. Is there any tip to resolve it? GPU is NVIDIA T1000. kindly help.

Is there any possibility to get the individual style transfer by providing specific input sample voice while using audioLDM2 for for text-to-speech instead of random voice? If any help or...

Is there any way to use more than 1 GPU using this script? Please guide. i tried several ways and it didn't work.