Clive

@naymaraq thanks will try it out.

Hi thanks for the reply. Will follow the steps , super thanks for the Voxpopuli tip How did u deal with long audios. ? I hd tried using ctc_segmentation with...

point 2 : Dropped words with too-low and too-high a character rate (which implies the ground truth label is incorrect). why do I drop samples with too-low sampling character rate?...

Hey so with this pr the I don't need to define max_step param for any scheduler ?

one way I found around this was by removing the callback

Hi @titu1994 I have successfully resumed training, the only change made is have added a new training dataset. When resuming from the prev .ckpt checkpoint it says not a end-of-epoch...

anyone?

I was able to install it using brew mecab.

Had same problem with spanish model es_ES/m-ailabs_low this has 3 voices 2 male and 1 female for all same problem. A quick fix was to add , instead of ....

But for es_ES/carlfm_low I didn't get same issue.