MagicSource

从效果来看，还可以啊

不是可以直接作为reference吗，我还没有训练，还要自己训练么. 打标都是funasr

@wangqixun which model were using here?

whisper stt support mandrain. doesn't know about tts. I think tts would be a little bit harder.

@jpc multilangual tts is an ambitious goal, for Mandrain, TBH, there is no very good open dataset. Biaobei (Baker) could be used as experiment.


No

Can u also share pretraining script? Which tuning projector and vision encoder with stage 1 and stage 2? This not same as llava.

我跑的34b-vl，你这个是真炸了。 多测试几张图片，我发现Yi训练的这个多模态，在某些图片上容易炸

官方科比的图片是没有问题的，换一个其他的大概率炸，98%。 不知何故