Tts: librosa.util.exceptions.ParameterError: Target size (38) must be at least input size (1100)

[nowingnet]

After running the server( python3 server/server.py -c server/conf.json),
I tried to test text through web browser.

But, Message "librosa.util.exceptions.ParameterError: Target size (38) must be at least input size (1100)" has occurred

Below is the full message.

File "tts/utils/audio.py", line 110, in _griffin_lim
angles = np.exp(1j * np.angle(self._stft(y)))
File "tts/utils/audio.py", line 124, in _stft
y=y, n_fft=self.n_fft, hop_length=self.hop_length, win_length=self.win_length)
File "tts/lib/python3.6/site-packages/librosa-0.5.1-py3.6.egg/librosa/core/spectrum.py", line 152, in stft
fft_window = util.pad_center(fft_window, n_fft)
File "tts/lib/python3.6/site-packages/librosa-0.5.1-py3.6.egg/librosa/util/utils.py", line 287, in pad_center
'at least input size ({:d})').format(size, n))
librosa.util.exceptions.ParameterError: Target size (38) must be at least input size (1100)

[752377941]

I have the same problem as this. Can u tell me how to resolve it?

[erogol]

I don't know what is it in particular. It does not seem to be TTS problem but librosa.

[nowingnet]

I found that the problem was sequence to call the function.

in server/synthesizer.py
27 line

self.ap = AudioProcessor(
config.sample_rate,
config.num_mels,
config.min_level_db,
config.frame_shift_ms,
config.frame_length_ms,
config.ref_level_db,
config.num_freq,
config.power,
config.preemphasis, <= this is the wrong sequence ...
griffin_lim_iters=60)

[erogol]

Ohh see. Thx for flagging it. But server part of the code only warranted for the server branch. Sorry about it. If it is always welcome to have a nice looking PR :+1:

[752377941]

我发现问题是调用函数的序列。

在server / synthesizer.py
27行

self.ap = AudioProcessor（
config.sample_rate，
config.num_mels，
config.min_level_db，
config.frame_shift_ms，
config.frame_length_ms，
config.ref_level_db，
config.num_freq，
config.power，
config.preemphasis，<=这是错误的序列。 ..
griffin_lim_iters = 60）

thanks