RVC-Project
[Bug] Model Files Fail to Train
Using the current version (pulled moments before writing this), I try to 'one click train' and it performs the Process Data / Feature Extraction steps but then then crashes without training any models. This is in addition to another bug (167) that is unable to write the index file.
(truncated text) now-169,all-160,7_1.wav,(149, 256) 7_2.wav-contains nan 7_4.wav-contains nan 8_0.wav-contains nan 8_1.wav-contains nan 8_3.wav-contains nan 8_4.wav-contains nan 9_1.wav-contains nan 9_2.wav-contains nan all-feature-done
Traceback (most recent call last):
File "/home/user/Retrieval-based-Voice-Conversion-WebUI/train_nsf_sim_cache_sid_load_pretrain.py", line 7, in
The error log is truncated here is the entire output start to finish: (Retrieval-based-Voice-Conversion-WebUI) user@machine:~/Retrieval-based-Voice-Conversion-WebUI$ python infer-web.py Use Language: en_US 16系显卡强制单精度 Running on local URL: http://0.0.0.0:7865 start preprocess ['trainset_preprocess_pipeline_print.py', '/home/user/Music/dataset_hj/40k/Minidata', '40000', '8', '/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test', 'False'] /home/user/Music/dataset_hj/40k/Minidata/04_fai_04_28_111.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/10_fai_10_28_106.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/22_fai_22_28_004.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/24_fai_24_28_064.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_014.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_059.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/SUPER_BOWL_ZUCCHINI_Raw_Audio_131935027_000.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/04_fai_04_28_118.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/12_fai_12_28_013.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/22_fai_22_28_027.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/24_fai_24_28_066.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_020.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_063.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/SUPER_BOWL_ZUCCHINI_Raw_Audio_131935027_004.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/09_fai_09_28_038.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/14_fai_14_28_247.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/22_fai_22_28_028.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/25_fai_25_28_043.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_021.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_066-2.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/107badstuffvx_000.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/15_fai_15_28_164.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/22_fai_22_28_104.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/25_fai_25_28_050.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_031.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_072.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/107badstuffvx_003.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/16_fai_16_28_241.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/23_fai_23_28_109.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/25_fai_25_28_082.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_032-1.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_073.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/107badstuffvx_004.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/16_fai_16_28_245.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/23_fai_23_28_146.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/25_fai_25_28_122.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_032-2.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_086.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/107badstuffvx_005.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/19_fai_19_28_050.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/23_fai_23_28_150.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/25_fai_25_28_188.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_039.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_100.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/10_fai_10_28_002.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/21_fai_21_28_139.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/24_fai_24_28_040.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_000.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_041.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_103.wav->Suc. end preprocess start preprocess ['trainset_preprocess_pipeline_print.py', '/home/user/Music/dataset_hj/40k/Minidata', '40000', '8', '/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test', 'False'] /home/user/Music/dataset_hj/40k/Minidata/04_fai_04_28_111.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/10_fai_10_28_106.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/22_fai_22_28_004.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/24_fai_24_28_064.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_014.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_059.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/SUPER_BOWL_ZUCCHINI_Raw_Audio_131935027_000.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/04_fai_04_28_118.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/12_fai_12_28_013.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/22_fai_22_28_027.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/24_fai_24_28_066.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_020.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_063.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/SUPER_BOWL_ZUCCHINI_Raw_Audio_131935027_004.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/09_fai_09_28_038.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/14_fai_14_28_247.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/22_fai_22_28_028.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/25_fai_25_28_043.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_021.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_066-2.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/107badstuffvx_000.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/15_fai_15_28_164.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/22_fai_22_28_104.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/25_fai_25_28_050.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_031.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_072.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/107badstuffvx_003.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/16_fai_16_28_241.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/23_fai_23_28_109.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/25_fai_25_28_082.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_032-1.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_073.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/107badstuffvx_004.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/16_fai_16_28_245.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/23_fai_23_28_146.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/25_fai_25_28_122.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_032-2.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_086.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/107badstuffvx_005.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/19_fai_19_28_050.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/23_fai_23_28_150.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/25_fai_25_28_188.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_039.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_100.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/10_fai_10_28_002.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/21_fai_21_28_139.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/24_fai_24_28_040.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_000.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_041.wav->Suc. /home/user/Music/dataset_hj/40k/Minidata/BBS1E1_103.wav->Suc. end preprocess
['extract_f0_print.py', '/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test', '8', 'harvest']
todo-f0-22
f0ing,now-0,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_0.wav
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
todo-f0-21
f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_1.wav
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
todo-f0-21
f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_2.wav
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
todo-f0-21
f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_4.wav
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
todo-f0-21
f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_5.wav
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
todo-f0-21
f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/10_0.wav
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
todo-f0-21
f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/10_1.wav
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
todo-f0-21
f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/10_2.wav
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:89: DeprecationWarning: np.int is a deprecated alias for the builtin int. To silence this warning, use int by itself. Doing this will not modify any behavior and is safe. When replacing np.int, you may wish to use e.g. np.int64 or np.int32 to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
f0_coarse = np.rint(f0_mel).astype(np.int)
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:89: DeprecationWarning: np.int is a deprecated alias for the builtin int. To silence this warning, use int by itself. Doing this will not modify any behavior and is safe. When replacing np.int, you may wish to use e.g. np.int64 or np.int32 to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
f0_coarse = np.rint(f0_mel).astype(np.int)
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:89: DeprecationWarning: np.int is a deprecated alias for the builtin int. To silence this warning, use int by itself. Doing this will not modify any behavior and is safe. When replacing np.int, you may wish to use e.g. np.int64 or np.int32 to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
f0_coarse = np.rint(f0_mel).astype(np.int)
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:89: DeprecationWarning: np.int is a deprecated alias for the builtin int. To silence this warning, use int by itself. Doing this will not modify any behavior and is safe. When replacing np.int, you may wish to use e.g. np.int64 or np.int32 to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
f0_coarse = np.rint(f0_mel).astype(np.int)
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:89: DeprecationWarning: np.int is a deprecated alias for the builtin int. To silence this warning, use int by itself. Doing this will not modify any behavior and is safe. When replacing np.int, you may wish to use e.g. np.int64 or np.int32 to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
f0_coarse = np.rint(f0_mel).astype(np.int)
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:89: DeprecationWarning: np.int is a deprecated alias for the builtin int. To silence this warning, use int by itself. Doing this will not modify any behavior and is safe. When replacing np.int, you may wish to use e.g. np.int64 or np.int32 to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
f0_coarse = np.rint(f0_mel).astype(np.int)
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:89: DeprecationWarning: np.int is a deprecated alias for the builtin int. To silence this warning, use int by itself. Doing this will not modify any behavior and is safe. When replacing np.int, you may wish to use e.g. np.int64 or np.int32 to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
f0_coarse = np.rint(f0_mel).astype(np.int)
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:89: DeprecationWarning: np.int is a deprecated alias for the builtin int. To silence this warning, use int by itself. Doing this will not modify any behavior and is safe. When replacing np.int, you may wish to use e.g. np.int64 or np.int32 to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
f0_coarse = np.rint(f0_mel).astype(np.int)
/home/user/Retrieval-based-Voice-Conversion-WebUI/extract_f0_print.py:38: FutureWarning: Pass sr=16000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
x, sr = librosa.load(path, self.fs) # , res_type='soxr_vhq'
f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/18_3.wav
f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/18_0.wav
f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/18_1.wav
f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/19_0.wav
f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/16_3.wav
f0ing,now-4,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/16_1.wav
f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/17_0.wav
f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/17_2.wav
f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_3.wav
f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/25_0.wav
f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_5.wav
f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/25_1.wav
f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_1.wav
f0ing,now-8,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/23_4.wav
f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_2.wav
f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_6.wav
f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/33_0.wav
f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/33_3.wav
f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/34_0.wav
f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/32_2.wav
f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/32_0.wav
f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/31_2.wav
f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/33_1.wav
f0ing,now-12,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/31_0.wav
f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/45_3.wav
f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/44_3.wav
f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/45_1.wav
f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/45_4.wav
f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/44_0.wav
f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/44_1.wav
f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/45_2.wav
f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/8_4.wav
f0ing,now-16,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/43_2.wav
f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/8_0.wav
f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/9_1.wav
f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/7_2.wav
f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/8_1.wav
f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/8_3.wav
f0ing,now-20,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/7_1.wav
f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/7_4.wav
['extract_f0_print.py', '/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test', '8', 'harvest']
todo-f0-22
f0ing,now-0,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_0.wav
todo-f0-21
f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_1.wav
todo-f0-21
f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_2.wav
todo-f0-21
f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_4.wav
todo-f0-21
f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_5.wav
todo-f0-21
f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/10_0.wav
todo-f0-21
f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/10_1.wav
todo-f0-21
f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/10_2.wav
f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/18_3.wav
f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/18_0.wav
f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/18_1.wav
f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/19_0.wav
f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/16_3.wav
f0ing,now-4,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/16_1.wav
f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/17_0.wav
f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/17_2.wav
f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_3.wav
f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/25_0.wav
f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_5.wav
f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/25_1.wav
f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_1.wav
f0ing,now-8,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/23_4.wav
f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_2.wav
f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_6.wav
f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/33_0.wav
f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/33_3.wav
f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/34_0.wav
f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/32_2.wav
f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/32_0.wav
f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/31_2.wav
f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/33_1.wav
f0ing,now-12,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/31_0.wav
f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/45_3.wav
f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/44_3.wav
f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/45_1.wav
f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/45_4.wav
f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/44_0.wav
f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/44_1.wav
f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/45_2.wav
f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/8_4.wav
f0ing,now-16,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/43_2.wav
f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/8_0.wav
f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/9_1.wav
f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/7_2.wav
f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/8_1.wav
f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/8_3.wav
f0ing,now-20,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/7_1.wav
f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/7_4.wav
['extract_feature_print.py', 'cuda:0', '1', '0', '0', '/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test'] /home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test load model(s) from hubert_base.pt 2023-04-28 21:17:53 | INFO | fairseq.tasks.hubert_pretraining | current directory is /home/user/Retrieval-based-Voice-Conversion-WebUI 2023-04-28 21:17:53 | INFO | fairseq.tasks.hubert_pretraining | HubertPretrainingTask Config {'_name': 'hubert_pretraining', 'data': 'metadata', 'fine_tuning': False, 'labels': ['km'], 'label_dir': 'label', 'label_rate': 50.0, 'sample_rate': 16000, 'normalize': False, 'enable_padding': False, 'max_keep_size': None, 'max_sample_size': 250000, 'min_sample_size': 32000, 'single_target': False, 'random_crop': True, 'pad_audio': False} 2023-04-28 21:17:53 | INFO | fairseq.models.hubert.hubert | HubertModel Config: {'_name': 'hubert', 'label_rate': 50.0, 'extractor_mode': default, 'encoder_layers': 12, 'encoder_embed_dim': 768, 'encoder_ffn_embed_dim': 3072, 'encoder_attention_heads': 12, 'activation_fn': gelu, 'layer_type': transformer, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'encoder_layerdrop': 0.05, 'dropout_input': 0.1, 'dropout_features': 0.1, 'final_dim': 256, 'untie_final_proj': True, 'layer_norm_first': False, 'conv_feature_layers': '[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 2', 'conv_bias': False, 'logit_temp': 0.1, 'target_glu': False, 'feature_grad_mult': 0.1, 'mask_length': 10, 'mask_prob': 0.8, 'mask_selection': static, 'mask_other': 0.0, 'no_mask_overlap': False, 'mask_min_space': 1, 'mask_channel_length': 10, 'mask_channel_prob': 0.0, 'mask_channel_selection': static, 'mask_channel_other': 0.0, 'no_mask_channel_overlap': False, 'mask_channel_min_space': 1, 'conv_pos': 128, 'conv_pos_groups': 16, 'latent_temp': [2.0, 0.5, 0.999995], 'skip_masked': False, 'skip_nomask': False, 'checkpoint_activations': False, 'required_seq_len_multiple': 2, 'depthwise_conv_kernel_size': 31, 'attn_type': '', 'pos_enc_type': 'abs', 'fp16': False} move model to cuda all-feature-169 0_0.wav-contains nan now-169,all-0,0_0.wav,(149, 256) 0_1.wav-contains nan 0_2.wav-contains nan 0_4.wav-contains nan 0_5.wav-contains nan 10_0.wav-contains nan 10_1.wav-contains nan 10_2.wav-contains nan 10_4.wav-contains nan 10_5.wav-contains nan 11_0.wav-contains nan 11_1.wav-contains nan 11_2.wav-contains nan 11_4.wav-contains nan 11_5.wav-contains nan 12_0.wav-contains nan 12_2.wav-contains nan now-169,all-16,12_2.wav,(149, 256) 12_4.wav-contains nan 12_5.wav-contains nan 13_0.wav-contains nan 13_1.wav-contains nan 13_3.wav-contains nan 13_4.wav-contains nan 14_0.wav-contains nan 14_1.wav-contains nan 14_2.wav-contains nan 14_4.wav-contains nan 15_0.wav-contains nan 15_1.wav-contains nan 15_2.wav-contains nan 15_4.wav-contains nan 15_5.wav-contains nan 16_1.wav-contains nan now-169,all-32,16_1.wav,(149, 256) 16_3.wav-contains nan 17_0.wav-contains nan 17_2.wav-contains nan 18_0.wav-contains nan 18_1.wav-contains nan 18_3.wav-contains nan 19_0.wav-contains nan 19_1.wav-contains nan 19_2.wav-contains nan 19_4.wav-contains nan 19_5.wav-contains nan 1_0.wav-contains nan 1_1.wav-contains nan 1_2.wav-contains nan 1_4.wav-contains nan 20_0.wav-contains nan now-169,all-48,20_0.wav,(149, 256) 20_1.wav-contains nan 20_2.wav-contains nan 20_4.wav-contains nan 21_0.wav-contains nan 21_1.wav-contains nan 21_2.wav-contains nan 21_4.wav-contains nan 21_5.wav-contains nan 22_0.wav-contains nan 22_2.wav-contains nan 22_4.wav-contains nan 22_5.wav-contains nan 23_0.wav-contains nan 23_1.wav-contains nan 23_2.wav-contains nan 23_4.wav-contains nan now-169,all-64,23_4.wav,(115, 256) 24_1.wav-contains nan 24_2.wav-contains nan 24_3.wav-contains nan 24_5.wav-contains nan 24_6.wav-contains nan 25_0.wav-contains nan 25_1.wav-contains nan 25_2.wav-contains nan 25_4.wav-contains nan 25_5.wav-contains nan 26_0.wav-contains nan 26_2.wav-contains nan 27_0.wav-contains nan 27_1.wav-contains nan 27_3.wav-contains nan 28_0.wav-contains nan now-169,all-80,28_0.wav,(149, 256) 28_1.wav-contains nan 28_2.wav-contains nan 28_4.wav-contains nan 28_5.wav-contains nan 29_0.wav-contains nan 29_2.wav-contains nan 29_3.wav-contains nan 2_0.wav-contains nan 2_1.wav-contains nan 2_2.wav-contains nan 2_4.wav-contains nan 30_0.wav-contains nan 30_1.wav-contains nan 30_3.wav-contains nan 30_4.wav-contains nan 31_0.wav-contains nan now-169,all-96,31_0.wav,(149, 256) 31_2.wav-contains nan 32_0.wav-contains nan 32_2.wav-contains nan 33_0.wav-contains nan 33_1.wav-contains nan 33_3.wav-contains nan 34_0.wav-contains nan 34_1.wav-contains nan 34_3.wav-contains nan 35_0.wav-contains nan 35_2.wav-contains nan 36_0.wav-contains nan 36_2.wav-contains nan 37_0.wav-contains nan 37_1.wav-contains nan 37_3.wav-contains nan now-169,all-112,37_3.wav,(84, 256) 38_0.wav-contains nan 38_2.wav-contains nan 39_0.wav-contains nan 39_1.wav-contains nan 39_3.wav-contains nan 3_0.wav-contains nan 3_2.wav-contains nan 40_0.wav-contains nan 40_2.wav-contains nan 41_0.wav-contains nan 41_2.wav-contains nan 42_0.wav-contains nan 42_1.wav-contains nan 42_3.wav-contains nan 43_0.wav-contains nan 43_2.wav-contains nan now-169,all-128,43_2.wav,(117, 256) 44_0.wav-contains nan 44_1.wav-contains nan 44_3.wav-contains nan 45_1.wav-contains nan 45_2.wav-contains nan 45_3.wav-contains nan 45_4.wav-contains nan 45_5.wav-contains nan 45_6.wav-contains nan 46_0.wav-contains nan 46_2.wav-contains nan 47_0.wav-contains nan 47_2.wav-contains nan 48_0.wav-contains nan 48_2.wav-contains nan 48_3.wav-contains nan now-169,all-144,48_3.wav,(42, 256) 49_0.wav-contains nan 49_2.wav-contains nan 49_4.wav-contains nan 4_0.wav-contains nan 4_1.wav-contains nan 4_3.wav-contains nan 5_0.wav-contains nan 5_1.wav-contains nan 5_3.wav-contains nan 6_0.wav-contains nan 6_1.wav-contains nan 6_2.wav-contains nan 6_3.wav-contains nan 6_5.wav-contains nan 7_0.wav-contains nan 7_1.wav-contains nan now-169,all-160,7_1.wav,(149, 256) 7_2.wav-contains nan 7_4.wav-contains nan 8_0.wav-contains nan 8_1.wav-contains nan 8_3.wav-contains nan 8_4.wav-contains nan 9_1.wav-contains nan 9_2.wav-contains nan all-feature-done ['extract_f0_print.py', '/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test', '8', 'harvest'] todo-f0-22 f0ing,now-0,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_0.wav todo-f0-21 f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_1.wav todo-f0-21 f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_2.wav todo-f0-21 f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_4.wav todo-f0-21 f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/0_5.wav todo-f0-21 f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/10_0.wav todo-f0-21 f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/10_1.wav todo-f0-21 f0ing,now-0,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/10_2.wav f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/18_3.wav f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/18_0.wav f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/18_1.wav f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/19_0.wav f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/16_3.wav f0ing,now-4,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/16_1.wav f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/17_0.wav f0ing,now-4,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/17_2.wav f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_3.wav f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/25_0.wav f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_5.wav f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/25_1.wav f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_1.wav f0ing,now-8,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/23_4.wav f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_2.wav f0ing,now-8,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/24_6.wav f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/33_0.wav f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/33_3.wav f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/34_0.wav f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/32_2.wav f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/32_0.wav f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/31_2.wav f0ing,now-12,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/33_1.wav f0ing,now-12,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/31_0.wav f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/45_3.wav f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/44_3.wav f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/45_1.wav f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/45_4.wav f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/44_0.wav f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/44_1.wav f0ing,now-16,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/45_2.wav f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/8_4.wav f0ing,now-16,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/43_2.wav f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/8_0.wav f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/9_1.wav f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/7_2.wav f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/8_1.wav f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/8_3.wav f0ing,now-20,all-22,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/7_1.wav f0ing,now-20,all-21,-/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test/1_16k_wavs/7_4.wav ['extract_feature_print.py', 'cuda:0', '1', '0', '0', '/home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test'] /home/user/Retrieval-based-Voice-Conversion-WebUI/logs/mi-test load model(s) from hubert_base.pt move model to cuda all-feature-169 0_0.wav-contains nan now-169,all-0,0_0.wav,(149, 256) 0_1.wav-contains nan 0_2.wav-contains nan 0_4.wav-contains nan 0_5.wav-contains nan 10_0.wav-contains nan 10_1.wav-contains nan 10_2.wav-contains nan 10_4.wav-contains nan 10_5.wav-contains nan 11_0.wav-contains nan 11_1.wav-contains nan 11_2.wav-contains nan 11_4.wav-contains nan 11_5.wav-contains nan 12_0.wav-contains nan 12_2.wav-contains nan now-169,all-16,12_2.wav,(149, 256) 12_4.wav-contains nan 12_5.wav-contains nan 13_0.wav-contains nan 13_1.wav-contains nan 13_3.wav-contains nan 13_4.wav-contains nan 14_0.wav-contains nan 14_1.wav-contains nan 14_2.wav-contains nan 14_4.wav-contains nan 15_0.wav-contains nan 15_1.wav-contains nan 15_2.wav-contains nan 15_4.wav-contains nan 15_5.wav-contains nan 16_1.wav-contains nan now-169,all-32,16_1.wav,(149, 256) 16_3.wav-contains nan 17_0.wav-contains nan 17_2.wav-contains nan 18_0.wav-contains nan 18_1.wav-contains nan 18_3.wav-contains nan 19_0.wav-contains nan 19_1.wav-contains nan 19_2.wav-contains nan 19_4.wav-contains nan 19_5.wav-contains nan 1_0.wav-contains nan 1_1.wav-contains nan 1_2.wav-contains nan 1_4.wav-contains nan 20_0.wav-contains nan now-169,all-48,20_0.wav,(149, 256) 20_1.wav-contains nan 20_2.wav-contains nan 20_4.wav-contains nan 21_0.wav-contains nan 21_1.wav-contains nan 21_2.wav-contains nan 21_4.wav-contains nan 21_5.wav-contains nan 22_0.wav-contains nan 22_2.wav-contains nan 22_4.wav-contains nan 22_5.wav-contains nan 23_0.wav-contains nan 23_1.wav-contains nan 23_2.wav-contains nan 23_4.wav-contains nan now-169,all-64,23_4.wav,(115, 256) 24_1.wav-contains nan 24_2.wav-contains nan 24_3.wav-contains nan 24_5.wav-contains nan 24_6.wav-contains nan 25_0.wav-contains nan 25_1.wav-contains nan 25_2.wav-contains nan 25_4.wav-contains nan 25_5.wav-contains nan 26_0.wav-contains nan 26_2.wav-contains nan 27_0.wav-contains nan 27_1.wav-contains nan 27_3.wav-contains nan 28_0.wav-contains nan now-169,all-80,28_0.wav,(149, 256) 28_1.wav-contains nan 28_2.wav-contains nan 28_4.wav-contains nan 28_5.wav-contains nan 29_0.wav-contains nan 29_2.wav-contains nan 29_3.wav-contains nan 2_0.wav-contains nan 2_1.wav-contains nan 2_2.wav-contains nan 2_4.wav-contains nan 30_0.wav-contains nan 30_1.wav-contains nan 30_3.wav-contains nan 30_4.wav-contains nan 31_0.wav-contains nan now-169,all-96,31_0.wav,(149, 256) 31_2.wav-contains nan 32_0.wav-contains nan 32_2.wav-contains nan 33_0.wav-contains nan 33_1.wav-contains nan 33_3.wav-contains nan 34_0.wav-contains nan 34_1.wav-contains nan 34_3.wav-contains nan 35_0.wav-contains nan 35_2.wav-contains nan 36_0.wav-contains nan 36_2.wav-contains nan 37_0.wav-contains nan 37_1.wav-contains nan 37_3.wav-contains nan now-169,all-112,37_3.wav,(84, 256) 38_0.wav-contains nan 38_2.wav-contains nan 39_0.wav-contains nan 39_1.wav-contains nan 39_3.wav-contains nan 3_0.wav-contains nan 3_2.wav-contains nan 40_0.wav-contains nan 40_2.wav-contains nan 41_0.wav-contains nan 41_2.wav-contains nan 42_0.wav-contains nan 42_1.wav-contains nan 42_3.wav-contains nan 43_0.wav-contains nan 43_2.wav-contains nan now-169,all-128,43_2.wav,(117, 256) 44_0.wav-contains nan 44_1.wav-contains nan 44_3.wav-contains nan 45_1.wav-contains nan 45_2.wav-contains nan 45_3.wav-contains nan 45_4.wav-contains nan 45_5.wav-contains nan 45_6.wav-contains nan 46_0.wav-contains nan 46_2.wav-contains nan 47_0.wav-contains nan 47_2.wav-contains nan 48_0.wav-contains nan 48_2.wav-contains nan 48_3.wav-contains nan now-169,all-144,48_3.wav,(42, 256) 49_0.wav-contains nan 49_2.wav-contains nan 49_4.wav-contains nan 4_0.wav-contains nan 4_1.wav-contains nan 4_3.wav-contains nan 5_0.wav-contains nan 5_1.wav-contains nan 5_3.wav-contains nan 6_0.wav-contains nan 6_1.wav-contains nan 6_2.wav-contains nan 6_3.wav-contains nan 6_5.wav-contains nan 7_0.wav-contains nan 7_1.wav-contains nan now-169,all-160,7_1.wav,(149, 256) 7_2.wav-contains nan 7_4.wav-contains nan 8_0.wav-contains nan 8_1.wav-contains nan 8_3.wav-contains nan 8_4.wav-contains nan 9_1.wav-contains nan 9_2.wav-contains nan all-feature-done
Traceback (most recent call last):
File "/home/user/Retrieval-based-Voice-Conversion-WebUI/train_nsf_sim_cache_sid_load_pretrain.py", line 7, in
- Try to increase the volume to avoid RVC cutting your normal voice out as silence.
- You got a
nanresult, so your wav or graphic card may be incompatible for training. @RVC-Boss will tell you whether we can fix that.
Alright, volume wise I've run https://github.com/henrymaas/AudioSlicer/ on my dataset so any silences were already stripped out and then ran the samples into a gentle saturator plugin, they are quite punchy and loud.
I'm attempting to re-running this with 2,034 samples ~ 4 hours of data and will see if it works better that way.
I'll also try to run this on another PC with more powerful dual GPU tomorrow am.
Thank you for taking a look at these.
Another observation I had was that this exact dataset and computer with previous versions of RVC was able to train models (just not output an index file) but that training feature seems to have regressed despite RVC previously being capable of doing so.
Still on my first PC with the much larger data set but it's saying a lot of samples are, for example:
1649_5.wav-contains nan
These samples had previously been recognized just fine, something might be wrong with how it's processing samples which is screwing up training. Unsure if that's related to the .index file failing to write but my initial assumption is it's a processing step causing issues.
@mr-segfault 16xx GPU can't extract half precision tensor feature. Nothing extracted and nothing trained.
You can try replace all ".half" to ".float" in the file "extract_feature_print.py", and try running "one-click training"again
Still have the error using 1070ti after replacing to ".float"
move model to cuda
all-feature-2111
all-feature-done
Traceback (most recent call last):
File "E:\PycharmProjects\Retrieval-based-Voice-Conversion-WebUI\train_nsf_sim_cache_sid_load_pretrain.py", line 7, in <module>
hps = utils.get_hparams()
File "E:\PycharmProjects\Retrieval-based-Voice-Conversion-WebUI\train\utils.py", line 363, in get_hparams
config = json.loads(data)
File "e:\anaconda3\lib\json\__init__.py", line 346, in loads
return _default_decoder.decode(s)
File "e:\anaconda3\lib\json\decoder.py", line 340, in decode
raise JSONDecodeError("Extra data", s, end)
json.decoder.JSONDecodeError: Extra data: line 47 column 1 (char 1046)
Still have the error using 1070ti after replacing to ".float"
move model to cuda all-feature-2111 all-feature-done Traceback (most recent call last): File "E:\PycharmProjects\Retrieval-based-Voice-Conversion-WebUI\train_nsf_sim_cache_sid_load_pretrain.py", line 7, in <module> hps = utils.get_hparams() File "E:\PycharmProjects\Retrieval-based-Voice-Conversion-WebUI\train\utils.py", line 363, in get_hparams config = json.loads(data) File "e:\anaconda3\lib\json\__init__.py", line 346, in loads return _default_decoder.decode(s) File "e:\anaconda3\lib\json\decoder.py", line 340, in decode raise JSONDecodeError("Extra data", s, end) json.decoder.JSONDecodeError: Extra data: line 47 column 1 (char 1046)
I have fixed it. Download the latest "config.py"and replace it.
I think this is now fixed as we're getting now further than this point but can leave it open for a day or two to let anyone else chime in with anything different
this is still occurring to me, no idea how to troubleshoot. I managed to get it to work once, no idea how
I am on RX6600xt, my dataset has ~60 files
I'm also getting #351
I was getting the "contains nan" message during feature extraction on my GTX 1660 Ti. I use master branch (commit 050ffd07e84a2227718a5cc6e7c7552bcdf2c10a). Fixed it with changing extract_feature_print.py lines containing ".half()", just removed halving. Seems there is a bug, because the code in the file is agnostic towards GPU half-precision ability.
