mrfakename

Hi, can we have the old-siri-like effect of "waves" instead of bars? Thanks!

License

3

Hi, Thanks for releasing this amazing project! MagicTime is licensed under Apache 2.0, but it says "The service is a research preview intended for non-commercial use only. Please contact us...

Hi, Would be nice to be able to use this using the `text-to-speech` pipeline. Thanks!

Long-form synthesis

5

Hi, Congrats on the release!! Is long form synthesis planned? Thank you!

Hello, I noticed that the website namekrea.com seems to be unreachable. When I try to access namekrea.com, Cloudflare gives me a 522 connection timed out error. The Wayback Machine last...

Int 4 quantization?

4

Hello, I'm relatively new here, but I was wondering if 4-bit quantization is possible to speed up inference. I know that [`tortoise-tts-fast`](https://github.com/152334H/tortoise-tts-fast) allows half precision, but I was wondering if...

Implement performance updates from XTTS-v2

1

Hi @manmay-nakhashi, Coqui recently released [XTTS-v2](https://huggingface.co/coqui/XTTS-v2). From the model card: > * 2 new languages; Hungarian and Korean > * Architectural improvements for speaker conditioning. > * Enables the use...

Tortoise TTS tries to download & replace model even though it already exists w/ custom model folder My code: ```python from tortoise import api from tortoise import utils import torchaudio...

* Minor updates * Prepare for MPS support for the fast API ([this PyTorch PR](https://github.com/pytorch/pytorch/pull/99272) must be merged before MPS support can be fully added - this just makes it...

Fast API on CPU + MPS GPU

1

Hi @manmay-nakhashi, are you planning to support the fast API work on CPU + MPS GPU? Thanks!