Comments (4)
The total encoder/decoder delay is actually 100ms.
from lyra.
Hi, thanks for the reply. But when I look at the decoded waveform and the original waveform, as show in the figure above, it seems not be 100ms? may be a little shorter?
from lyra.
There are 2 factors at play here. First, since you are measuring the delay from the input to output file, it doesn't take into account the time it takes to fill the buffer for the initial step, which adds an additional 40ms. So from the files you should be seeing something similar to 60ms of delay.
Additionally, these generative models can mess with the phase and delay withing a frame a bit, which means that the exact delay of a pair of files would rarely line up exactly with the estimated one.
from lyra.
The delay was reduced to 20ms in the new Lyra 1.2.0 release. But if you re-run your experiment you'll see the files basically line up, since all the delay is only from buffering.
from lyra.
Related Issues (20)
- Linux build HOT 1
- ANDROID BUILD HOT 1
- Can't load TFLite output_details for quantizer model (encode) HOT 3
- When will lyra support ios platform? HOT 1
- The decoding CPU is too high. Is there any way to reduce it?
- model structure of lyra 1.3.2
- About crash problem with kInternalSampleRateHz set to 32k
- Android app built as per readme crashes (on Samsung S23) HOT 1
- how to read the encoded data in the sample1_16kHz.lyra file into python/numpy array?
- Directly provide the executable download address HOT 3
- Is that possible to release the model coeffs with codebook size=1024?
- Is it possible to still run the V1 model with the latest API? Or only V2
- LMCodec HOT 2
- Build fails on MacOS due to bad Tensorflow link HOT 1
- Noise is being added to generated speech in Python E2E flow (TFLite Models) HOT 2
- The Lyra Parameters
- bazel build -c opt lyra/cli_example:encoder_main
- support of sdk 34 and ndk
- Why does the sampling result need to be multiplied by 256?
- cannot build --config=android_arm64
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from lyra.