MoonInTheRiver / DiffSinger

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code
MIT License
4.35k stars 715 forks source link

处理数据的时候报这个问题 #109

Open wangjiancheng-123 opened 5 months ago

wangjiancheng-123 commented 5 months ago

Traceback (most recent call last): File "/mnt/d/workspace/DiffSinger-master/utils/multiprocess_utils.py", line 13, in chunked_worker res = map_func(*arg) File "/mnt/d/workspace/DiffSinger-master/data_gen/singing/binarize.py", line 382, in process_item cls.get_pitch(wav_fn, wav, mel, ph, res) File "/mnt/d/workspace/DiffSinger-master/data_gen/singing/binarize.py", line 364, in get_pitch gt_f0, gt_pitch_coarse = get_pitch(wav, spec, hparams) File "/mnt/d/workspace/DiffSinger-master/data_gen/tts/data_gen_utils.py", line 174, in get_pitch f0 = np.pad(f0, [[lpad, rpad]], mode='constant') File "<__array_function__ internals>", line 200, in pad File "/home/wjc/anaconda3/envs/svc/lib/python3.8/site-packages/numpy/lib/arraypad.py", line 744, in pad pad_width = _as_pairs(pad_width, array.ndim, as_index=True) File "/home/wjc/anaconda3/envs/svc/lib/python3.8/site-packages/numpy/lib/arraypad.py", line 510, in _as_pairs raise ValueError("index can't contain negative values") ValueError: index can't contain negative values

ghost commented 5 months ago

Is this all the error logs or just part of it? These information is too blur and general. And without description on your testing environment, I would like to mention this question, which is another speech processing project, and pointed out that the changed length of training data is the problem. It may help. 这是所有错误日志还是只是其中的一部分?这些信息太模糊和笼统了。而且没有描述您的测试环境,我想提一下这个问题,这是另一个语音处理项目,它指出训练数据的长度变化是问题所在。也许它会有帮助。