JingHSY-dev comments

Results 5 comments of


                                            JingHSY-dev

Error loading audio file: failed to open file.

I met the same question

Error loading audio file: failed to open file.

I solved the question. first: Search for the ‘libopenh264.so.’ folder under the ‘dreamtalk’ environment.: find ~/anaconda3 -name libopenh264.so.* second: cp ~/conda_env_path/lib/libopenh264.so.6 ~/conda_env_path/lib/libopenh264.so.5 Check if it’s working properly using the ‘ffmpeg’...

Some weights of the model checkpoint at jonatasgrosman/wav2vec2-large-xlsr-53-english were not used when initializing Wav2Vec2Model: ['lm_head.weight', 'lm_head.bias']

I met the same question。

安装了v0.02 - rc，能正常打开web UI，但是添加图片和音频后，运行时报错，请问该怎么处理？

同问，检查发现checkpoints\auido2pose_00140-model.pth存在

安装了v0.02 - rc，能正常打开web UI，但是添加图片和音频后，运行时报错，请问该怎么处理？

app_sadtalker.py中（默认的checkpoints不在系统路径中） def sadtalker_demo(checkpoint_path='scripts/checkpoints', config_path='src/config', warpfn=None):