You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I haven't seen another issue, so this might just be a me problem, but I lack the ability to fix it myself.
When running python compute_statistics.py --config_path D:/AI/Testing/TTS/dataset/dataset/LJSpeech-1.1/config.json --output_path D:/AI/Testing/TTS/dataset/dataset/LJSpeech-1.1/stats.npy I'm greeted with this error after it starts processing;
Traceback (most recent call last):
File "D:\AI\Testing\TTS\TTS\bin\compute_statistics.py", line 96, in <module>
main()
File "D:\AI\Testing\TTS\TTS\bin\compute_statistics.py", line 61, in main
linear_sum += linear.sum(1)
ValueError: operands could not be broadcast together with shapes (47188,1) (51157,1) (47188,1)
To Reproduce
Run python compute_statistics.py (config path) (output path)
See error for some reason.
Expected behavior
No response
Logs
(TTS) D:\AI\Testing\TTS\TTS\bin>python compute_statistics.py --config_path D:/AI/Testing/TTS/dataset/dataset/LJSpeech-1.1/config.json --output_path D:/AI/Testing/TTS/dataset/dataset/LJSpeech-1.1/stats.npy
> Setting up Audio Processor...
|> sample_rate:22050
|> resample:False
|> num_mels:80
|> log_func:np.log10
|> min_level_db:-100
|> frame_shift_ms:None
|> frame_length_ms:None
|> ref_level_db:20
|> fft_size:1024
|> power:1.5
|> preemphasis:0.0
|> griffin_lim_iters:60
|> signal_norm:False
|> symmetric_norm:True
|> mel_fmin:0
|> mel_fmax:8000.0
|> pitch_fmin:1.0
|> pitch_fmax:640.0
|> spec_gain:20.0
|> stft_pad_mode:reflect
|> max_norm:4.0
|> clip_norm:True
|> do_trim_silence:True
|> trim_db:60
|> do_sound_norm:False
|> do_amp_to_db_linear:True
|> do_amp_to_db_mel:True
|> do_rms_norm:False
|> db_level:None
|> stats_path:None
|> base:10
|> hop_length:256
|> win_length:1024
|> Found 15425 files in D:\AI\Testing\TTS\dataset\dataset\LJSpeech-1.1
> There are 15425 files.
0%|| 0/15425 [00:00<?, ?it/s]D:\anaconda3\envs\TTS\lib\site-packages\librosa\core\spectrum.py:256: UserWarning: n_fft=1024 is too large for input signal of length=2
warnings.warn(
0%|| 1/15425 [00:11<47:45:51, 11.15s/it]
Traceback (most recent call last):
File "D:\AI\Testing\TTS\TTS\bin\compute_statistics.py", line 96, in<module>main()
File "D:\AI\Testing\TTS\TTS\bin\compute_statistics.py", line 61, in main
linear_sum += linear.sum(1)
ValueError: operands could not be broadcast together with shapes (47188,1) (51157,1) (47188,1)
Describe the bug
I haven't seen another issue, so this might just be a me problem, but I lack the ability to fix it myself.
When running
python compute_statistics.py --config_path D:/AI/Testing/TTS/dataset/dataset/LJSpeech-1.1/config.json --output_path D:/AI/Testing/TTS/dataset/dataset/LJSpeech-1.1/stats.npy
I'm greeted with this error after it starts processing;To Reproduce
python compute_statistics.py (config path) (output path)
Expected behavior
No response
Logs
Environment
Additional context
No response
The text was updated successfully, but these errors were encountered: