len_crop issue when train with VCTK dataset

[junseokoh1]

Thanks for your nice project and let us to use.

I guess the pre-trained model that this project give is only trained for validation with only 4 data(p225, p226, p227, p228)

So to reproduce the result of paper, i download VCTK dataset and as paper say i pick 40 speaker (40 speakers for zero-shot train), which is p225 ~ p269 ( maybe 40 ~ 43 speaker, also i change sampling rate to 16k)

When making train.pkl with make_matadata.py there is error with len_crop.

ValueError: 'a' cannot be empty unless no samples are taken

The default value of len_crop is 128, but there is shorter data in VCTK.

I want to know whether you just remove the len_crop part or just use VCTK data which is longer then 128.

Thanks for reading issue.

[junseokoh1]

Also there is about 400 utterance for each speaker

At make_metadata.py code, to use all data,
i replace

autovc/make_metadata.py

Lines 42 to 47 in 79dda70

	while tmp.shape[0] < len_crop:
	idx_alt = np.random.choice(candidates)
	tmp = np.load(os.path.join(dirName, speaker, fileList[idx_alt]))
	candidates = np.delete(candidates, np.argwhere(candidates==idx_alt))
	left = np.random.randint(0, tmp.shape[0]-len_crop)
	melsp = torch.from_numpy(tmp[np.newaxis, left:left+len_crop, :]).cuda()

to
melsp = torch.from_numpy(tmp[np.newaxis, :, :]).cuda()

[auspicious3000]

You could just skip the shorter utterances.

[fvgkjasdh]

每个说话者大约有 400 个话语

在 make_metadata.py 代码中，为了使用所有数据， 我替换

autovc/make_metadata.py

第 42 至 47 行 79dda70

while tmp.shape [ 0 ] < len_crop :​​
idx_alt = np.random.choice（候选人）​​​​
tmp = np.load ( os.path.join ( dirName , speaker , fileList [ idx_alt ] ) )​​​​
候选人 = np.delete (候选人，np.argwhere (候选人== idx_alt ) )​​​
left = np.random.randint ( 0 , tmp.shape [ 0 ] - len_crop )​​​​​​
melsp = torch.from_numpy ( tmp [ np.newaxis , left : left + len_crop ,: ] ) . cuda ( )

到
melsp = torch.from_numpy(tmp[np.newaxis, :, :]).cuda()

你好，你跳过之后训练出的模型，能够推理出高质量的音频吗？