dsplog
dsplog
used the model for training in another language. from the student model, the generated mel spectrogram seems to be close, but some bluriness is there.  tried...
thanks for sharing the amazing work. will it be possible to share universal model in the v2 configuration?
@jaywalnut310 : can you plz comment on adapting this model for zero shot or few shot tts voice conversion
Describe the bug This is not a bug, but trying to understand To Reproduce Steps to reproduce the behavior: If the training data size is larger inclduing LibriTTS clean, should...
can you please advise on usage of python wrapper of mlmorph analyzer for converting number to malayalam text. tried ``` from mlmorph import Analyser analyser = Analyser() analyser.analyse("100") ``` but...
converting the positionValues() code to python
seeing conflict when trying to load [mlphon](https://pypi.org/project/mlphon/) and mlmorph together the code snippet ``` from mlmorph import Generator from mlphon import PhoneticAnalyser generator = Generator() print('try1') print(generator.generate("കേരളം")) mlphon = PhoneticAnalyser()...
in the meldataset.py, could see that all wav files are resampled to 24000sps. however, as the MelSpectrogram() transform is called without `sample_rate` argument defaults to 16000sps. ``` to_mel = torchaudio.transforms.MelSpectrogram(...
fix for https://github.com/yl4579/PL-BERT/issues/29 and support for malaylam ``` text = 'hello (1200 - 1230)' out = normalize_text(text) print(out) hello (one thousand two hundred to one thousand two hundred thirty) ```
def add_edge(self, eid, frm, to, elb): """Add an edge to the graph.""" if (frm is self.vertices and to in self.vertices and to in self.vertices[frm].edges): return self if (frm is self.vertices...