-
Win10
显卡3080
CUDA 12.5
下载的README上的第三方windows整合包，点Generate后，大概500秒页面提示错误，控制台打印日志如下。
```
启动中，请耐心等待 bilibili@十字鱼 https://space.bilibili.com/893892
Already download the model.
Loads checkpoint b…
-
启动方式：musetalk，webrtc
启动命令：python app.py --model musetalk --transport webrtc --tts gpt-sovits --TTS_SERVER http://127.0.0.1:5000 --batch_size 16
模型：musetalk示例模型
 got an unexpected k…
-
PaddleTTS Error: No module named 'paddlespeech'
如果使用PaddleTTS，请先安装PaddleTTS环境
pip install -r requirements_paddle.txt
默认不使用LLM模型，直接回复问题，同时减少显存占用！
[nltk_data] Error loading averaged_perceptron_tagg…
-
你好，请问使用musetalk的时候，上传的视频有固定格式要求吗，为什么我的总报错呢
-
你好我想问一下Linly-Talker-win-all的museTalk怎么跑不起来啊
-
The model you trained works very well, but we use our data （about 2000 minutes) to train our model，the lip is bad and image is blur. Do you have any suggestions? Thanks
XH-B updated
4 months ago
-
In this work, the author adopted Whisper-tiny (d_model=384) to extract audio feature, while training UNet from scratch. I guess the reason behind training from scratch instead of loading pretrained SD…
-
以下是一些效果展示，包括人脸驱动，语音驱动，表情姿态动作迁移等：
https://github.com/Zejun-Yang/AniPortrait/assets/20749514/a4bd2a06-6be8-4ecf-bfa3-337e5dcff4bb
https://github.com/Zejun-Yang/AniPortrait/assets/20749514/087b…
-
ValueError: File E:\workplace\MuseTalk\results\input\outputxxx_mmajicmixRealv6Fp16_rmmusev_referencenet_caseclx09jgwh0000vsp05s0xtp8c_w960_h1280_t102_nb1_s9241040_p5ff69_w0.001_ms8.0_s0.8_g3.5_c-iclx0…