search

OpenTalker / video-retalking

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild
https://opentalker.github.io/video-retalking/
Apache License 2.0
6.04k stars 896 forks source link

step3 - TypeError: mel() takes 0 positional arguments but 2 positional arguments (and 3 keyword-only arguments) were given #179

Open cunjieliu opened 7 months ago

cunjieliu commented 7 months ago

TypeError: mel() takes 0 positional arguments but 2 positional arguments (and 3 keyword-only arguments) were given

cunjieliu commented 7 months ago

pip install librosa==0.8.0

Oyiyi commented 6 months ago

Thank you @cunjieliu it works originally but I noted "tts 0.22.0 requires tqdm>=4.64.1, which is not installed. tts 0.22.0 requires librosa>=0.10.0, but you have librosa 0.8.0 which is incompatible" error. Did you update the version of TTS, librosa and tqdm together?

What's your version of libraries?

cryptovalentin commented 5 months ago

same error who can resolve?

johndpope commented 1 month ago

in utils/audio.py line 100 update to add params

  return librosa.filters.mel(sr=hp.sample_rate, n_fft=hp.n_fft, n_mels=hp.num_mels,
                               fmin=hp.fmin, fmax=hp.fmax)