search

facebookarchive / loop

A method to generate speech across multiple speakers
Other
872 stars 158 forks source link

Any clue? Missing norm_info_mgc_lf0_vuv_bap_63_MVN.dat while prepossessing Lj Speech Dataset. #48

Open niravpatel2008 opened 6 years ago

niravpatel2008 commented 6 years ago

I am getting below error while preprocessing Lj Speech data set.

Traceback (most recent call last):
  File "extract_feats.py", line 1406, in <module>
    save_numpy_features()
  File "extract_feats.py", line 853, in save_numpy_features
    shutil.copy2(audio_norm_source, audio_norm_dest)
  File "/usr/lib/python2.7/shutil.py", line 130, in copy2
    copyfile(src, dst)
  File "/usr/lib/python2.7/shutil.py", line 82, in copyfile
    with open(src, 'rb') as fsrc:
IOError: [Errno 2] No such file or directory: '/home/jax/latest_features/final_acoustic_data/norm_info_mgc_lf0_vuv_bap_63_MVN.dat'
PetrochukM commented 6 years ago

Yup. Remember to uncomment these lines: https://gist.github.com/kastnerkyle/cc0ac48d34860c5bb3f9112f4d9a0300#file-extract_feats-py-L1029

niravpatel2008 commented 6 years ago

@PetrochukM will try soon and let you know.

thanks

niravpatel2008 commented 6 years ago

@PetrochukM

After uncommenting i got faced following error :

`2018-03-29 11:15:23,161 INFO acoustic_comp: processing file 1 of 1 : /root/preprocess/latest_features/merlin/egs/build_your_own_voice/s1/experiments/ my_new_voice/acoustic_model/data/nn_mgc_lf0_vuv_bap_63/.cmp Traceback (most recent call last): File "/root/preprocess/latest_features/merlin/src/run_merlin.py", line 1175, i n main_function(cfg) File "/root/preprocess/latest_features/merlin/src/run_merlin.py", line 693, in main_function acoustic_worker.prepare_nn_data(in_file_list_dict, nn_cmp_filelist, cfg.in dimension_dict, cfg.out_dimension_dict) File "/root/preprocess/latest_features/merlin/src/frontend/acoustic_base.py", line 122, in prepare_nn_data self.prepare_data(in_file_list_dict, out_file_list, in_dimension_dict, out_d imension_dict) File "/root/preprocess/latest_features/merlin/src/frontend/acoustic_compositio n.py", line 126, in prepare_data features, frame_number = io_funcs.load_binary_file_frame(in_file_name, in_fe ature_dim) File "/root/preprocess/latest_features/merlin/src/io_funcs/binary_io.py", line 64, in load_binary_file_frame fid_lab = open(file_name, 'rb') IOError: [Errno 2] No such file or directory: '/root/preprocess/latest_features/ merlin/egs/build_your_own_voice/s1/experiments/my_new_voice/acoustic_model/data/ mgc/.mgc'

PetrochukM commented 6 years ago

People were able to figure it out in this post: https://github.com/facebookresearch/loop/issues/11

Does that help?

niravpatel2008 commented 6 years ago

@PetrochukM have earlier tried those solutions but still having issue. may be i am struggling because i am new to synthesizing.

sausax commented 6 years ago

@niravpatel2008 Any success with LJ Dataset ?

wanshun123 commented 6 years ago

I had this error and had to install bandmat https://pypi.org/project/bandmat/ and lxml https://lxml.de/installation.html (in the logs many lines above there was a module not found error as it was trying to import these libraries).