YaoyaoChang
YaoyaoChang
您好,您的邮件我已经收到,我一定会尽快回复的!谢谢!【此为自动回复邮件】Hello, I've received your email. I will reply to you as soon as possible! Thank you! 【This is an automatic reply email】
you can filtering data in the `Streaming**DataLoader**.__iter__()` instead of `StreamingDataset.__iter__()`. Because the state_dict depends on the `num_sample_yielded` in `StreamingDataLoader`, you need to calculate the `num_sample_yielded` firstly, then filter the samples...
We do not plan to allow fine-tuning of the streaming model, due to potential DeepFake risks. Which new languages would you like?
Thanks for the interest! Is there any issue you’d like to ask about?
Since we don’t have access to an AMD GPU, it’s difficult for us to reproduce and resolve your issue directly. Thanks to [vatsalm1611](https://github.com/vatsalm1611?utm_source=chatgpt.com), please try [PR #51](https://github.com/microsoft/VibeVoice/pull/51?utm_source=chatgpt.com). If it works...
Env? Error message?
Looks like https://github.com/microsoft/VibeVoice/pull/72 fixed your problem — try it out and share how it goes!
before: > Speaker 1: sentence 1. sentence 2. ... sentence 10. after: > Speaker 1: sentence 1. > Speaker 1: sentence 2. > ... > Speaker 1: sentence 10. This...
At the moment, our team doesn’t have the bandwidth to work on Android deployment. Contributions from the community would be very welcome — if anyone is interested in tackling this,...