Roger Condori

Hello @zhanghanghitomi, I created a notebook to run the model on Colab. You can find it [here](https://colab.research.google.com/github/R3gm/InsightSolver-Colab/blob/main/SeamlessM4T.ipynb)

Hi, the crash might be due to an out-of-memory (OOM) problem. Have you monitored your system's memory while running the process?

Thanks @b4zz4, it seems like WhisperSpeech is only available in two languages for now

Hello, sorry for responding late. In Linux, you need to install ffmpeg, which might be causing the issue

Hello, The TTS generates segments individually and then combines them into a single audio file. Sometimes, the duration of these segments exceeds the expected timeframe, causing overlap. To compensate, the...

> Thanks for the great work! Is it possible to slow down the video itself so that the audio segment comes in at normal speed? Thank you! At the moment,...

I haven't heard of it before, but I'll definitely look into it, thanks!

Hi, I'll explore options for implementing multithreading in RVC. Regarding Piper TTS on Windows, I haven't tested it. However, I'll look into the Silero TTS you mentioned as a potential...

Hi @NeuroDonu, It's an incredible idea. First, we need to see if there's library compatibility because ultimately, I've had problems with that. If there are no issues with it and...

Understood, but let's ensure the stability given the potential compatibility issues Thanks