YYX666660

Got it! thx :)

Well, the data processing of my training and testing are the same. The case above happens when the sampling ratio are large (16k to 48k/ 8k to 48k), cause there...

About the [lost_file](https://github.com/xiph/LPCNet/tree/master/training_tf2/train_plc.py#L37), I try to use the [lossgen](https://gitlab.xiph.org/xiph/opus/-/tree/main/dnn/torch/lossgen) model to generate the txt, but I'm not sure how long and how many loss rate should be generated. Very confused...

Hi~ I've read the code and articles about FARGAN. In the latest opus 1.5.2 source code, FARGAN acts as a vocoder after the silk plc for improving the quality of...

Thank you so much for your reply! I'm a beginner of codec, and I'm not sure if my understanding is correct 🙏 In the Opus1.5.2 source code, when it comes...

> FARGAN is a complete vocoder just like LPCNet. In Opus, the FARGAN signal completely replaces (not enhance) the SILK PLC output. Hi~ @jmvalin. May I ask you a question...

hi @jmvalin. I want to ask a question about the time-consuming. Arm_neon inference is in the existing code. I measured the time consumption of running `opus_demo`(with compiling --enable_deep_plc) on a...

Thanks @jmvalin, got it. I've already used FARGAN. I add the -march=armv8.2-a+dotprod option for arm64 like this: ``` # autotools compile ./configure --enable-deep-plc CFLAGS="-DUSE_WEIGHTS_FILE" # before adding dotprod ./configure --enable-deep-plc...

Got it. The build system of Mac/iOS is different, I need to check the compile of iOS system. Thanks a lot for the explanation~ @jmvalin By the way, I'm still...

> > From the spectrogram on my end, extending the speech from 24kHz to 48kHz appears to be working fine. > > I’m not entirely sure if, by “the outputs...