-
Hi,
I have trained a vocoder model using parallel_wavegan on my own corpus and wondering if I can upload it just like TTS models (tacotron, fastspeech, etc) to huggingface and then use the ```vocoder…
-
**Is your feature request related to a problem? Please describe.**
Currently the api assumed English. This is a problem for other languages!
Some models / vocoders support multiple languages.
…
-
This is an umbrella issue to track progress and discuss priority items. Comments and requests are always welcome.
## MIlestones
- [x] ~ 4/26 (Sun): Refactor my jupyter-based code to python scrip…
-
In current implementation inference-time entire audio data proceesing at a time for recunstructing high quality signal.
Modified the processing logic & Observed performance degradation with proces…
-
Hi brentspell,
What is the PERFECT/BEST evaluation metric for BWE ? POLQA can be used for BWE evalution metric or not?
-
Is there a comparison between vocoders?
-
hello， when I analysis code to find world feat not used in code？I want to confirm that wav->sp->mgc(60) has been done in this repo? and the residual connection in xiaoice has been done in this repo? …
-
Thank you for your work and sharing.
Since I have to use the vocoder model on online sevice, I want to know:
Does the model has a certain receptive field so that I can do inference in stream mode?
…
-
Also, to this question: can other GAN vocoder be used, for example Hifigan | StyleMelgan from ParallelWaveGan?
-
Configuration json contains value of eps as 1e-9.
In the transformers.py there's
def searchsorted(bin_locations, inputs, eps=1e-6):
Whilst in another issue you say that spec must be (and eps as…