Open belr20 opened 3 years ago
Thanks. I've been banging my head on the keyboard trying to get all the dependencies satisfied. That was one.
Tensorflow is also one in my experience. I already have TF so removing it from the reqs got me through that.
Worth noting for future people that > v.8 they removed librosa_output_write_wav and replaced it with soundfile_write
pip install soundfile then:
prediction_denoise.py
import soundfile as sf
line 55:
sf.write(dir_save_prediction + audio_output_prediction, denoise_long[0, :], sample_rate)
Yesterday, i used the model for PREDICTION with librosa 0.8.0 in my conda environment.
In this 0.8.0 version
librosa.output.write_wav
(line 55 in prediction_denoise.py for example) is deprecated (cf. stackoverflow#63997969).So
librosa==0.6
has to be specified in requirements.txt.