boolw
boolw
我们试了好几种修改方法但是效果都不好，可以提供一下具体的修改方法吗？非常感谢
我们也是使用的`jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn`这个模型，我们尝试改了`self.audio_in_dim = 3503 和 self.audio_dim = 3503` 两次地方，但是训练出来视频口型和语音不对应，效果不理想，可以提供一下具体修改的方案吗？
@JuneoXIE Hello, we also use the model 'jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn', but the effect is not satisfactory. I see that you have similar problems. I don't know how your training support for Chinese...
Great, thanks for your reply
还有类似的： 50行：DB::table($table) 修正为 DB::table(DB::raw($table))
@davidzhao First of all, thank you very much for the reply from the Egress team. When we use the ParticipantEgress mode of the SDK, when we encounter a requirement for...
@davidzhao Of course, the resolution of WebRTC video is not fixed. Whenever upstream congestion is encountered, the publisher can publish lower bitrate/fps. This situation has indeed been missed by me....
I just tried it. There is a green screen when simulcast is turned on or off. I adjusted the resolution from 1280*720 to 640*480 and the green screen still appears....