-
Hey, first of all, great work!
Two things bug me though:
1. What's the semantic value of the HuBERT model you trained if it's using the first RVQ layer of the _acoustic_ tokenizer? I.e. the acoust…
-
Hm, I'm running into a similar issue with another Evenki-adapted English model, and adding --position_dependent_phones false no longer seems to be doing the trick. :/
mfa version 2.2…
-
Some tests take a long time. At the time of writing, this is the order of the tests. Some should be strategized to be shorter.
This ran with `-j 1`, so the tests didn't interfere with one another.
…
-
Hi there,
I'm currently working on occupancy models specifically geared towards passive acoustic monitoring, where sites are allowed to chance occupancy state throughout the acoustic deployment per…
-
Any way to use a different acoustic model?
-
Hi,
I use custom acoustic (_.am.bin) and language (_.lm.bin) models in Portuguese for Julius. How can I change the voxforge default acoustic and language models in juliusjs so that I can use my own p…
-
I am using [LJSpeech](https://keithito.com/LJ-Speech-Dataset/) dataset. It has 22500 Hz wav so I downsampled them to 16000 Hz. While the duration model converges, the acoustic model stops after some s…
-
Hello fairseq team!
#### Problem Summary
I've been trying to reproduce the results of [this paper](https://research.facebook.com/publications/hokkien-direct-speech-to-speech-translation/) for re…
-
I was thinking that it could be useful to have support for system combination at nnet output level. For e.g. we can use this feature to combine 2 chain models (e.g. TDNN-F and TDNN-LSTM) which use the…
-
Thanks for opensource the excellent work!
I was trying to train an AR(GPT) model on dac and xcodec with libritts, in my exp, the top10 acc for the first token of dac and xcodec is very close, around…