Loreto Parisi

so I came out with this solution that works for me ```python @classmethod def stanza2Json(self, doc, ensure_ascii = True, indent = 4): ''' convert stanza document to json string '''...

@tuan3w uhm same question for `Deep Voice 2`. By the way datasets should be the same referred in the Deep Voice 1 & 2 papers: http://research.baidu.com/deep-voice-2-multi-speaker-neural-text-speech/ See [here](http://research.baidu.com/wp-content/uploads/2017/05/Deep-Voice-2-Complete-Arxiv.pdf).

@nurtas-m confirmed that it works now! thanks a lot that's a important fix 💯

@nurtas-m so I'm missing the files generated in the `data/dict` folders when then training of my CMU-IPA dict ends. I have only the checkpoint model files: ``` :~/docker/g2p-seq2seq/data/dict/cmudict-ipa$ ls -l...

@nurtas-m ok thanks. Question. If the input dictionary will be split into train and test, when I run the evaluation, how to use the test dictionary only i.e. the **WER**...

@nurtas-m ok thanks a lot. The last problem is that when I do a training from scratch I cannot see the files ``` cmudict.dict.part.train cmudict.dict.part.dev cmudict.dict.part.test ``` in the `data/dict/cmudict-ipa/`...

I'm on the latest version (since I need the fix of the inference and frozen model stuff...).

Just adding that for me inference from a pre-trained dictionary it works with ``` setuptools>=41.0.0 tensorflow tensor2tensor ``` so with TF 1.14.0, latest T2T on pip3 and python 3.7.3. The...

@dohliam thanks! I will have a look to find a good dictionary for that. For the spelling part in IT there are the hunspell dictionaries here: https://github.com/loretoparisi/dictionaries adapted to HunSpell...

@dohliam You are welcome, as you said it's a good start! I think it's a good idea to use CMU Sphinx directly to generate a phonetic output using the model...