Comments (5)
report my results:
- use ffmpeg to downsample the source data from 48khz to 16khz.
- use pretrained model in the best_ckpt/ folder
- use CPU to do evaluation
In the following metrics the first numbers are from the TABLE I of the paper (https://arxiv.org/pdf/2209.11112.pdf), and the second ones are my results. All the results are similar except the SSNR.
PESQ: 3.41 --> 3.41
CSIG: 4.63 --> 4.67
CBAK: 3.94 --> 3.91
COVL: 4.12 --> 4.14
SSNR: 11.10 --> 10.68
STOI: 0.96 --> 0.96
despite the inconsistent numbers between code and paper, i'm quite satisfied the performance with our own data.
from cmgan.
We encountered the same problem, with the SSNR indicator only 10.4 and each indicator slightly lower
from cmgan.
We got some complains about SSNR and it is currently being checked.
from cmgan.
- use ffmpeg to downsample the source data from 48khz to 16khz
I want to ask if I use the VCTK-DEMAND dataset to train, whether I need downsample the trainset to 16khz first or input the original data.
from cmgan.
from cmgan.
Related Issues (20)
- RuntimeError: NCCL error in: /……/.cpp:957, invalid usage, NCCL version 21.0.3 HOT 5
- RuntimeError: permute(sparse_coo): number of dimensions in the tensor input does not match the length of the desired ordering of dimensions i.e. input.dim() = 3 is not equal to len(dims) = 4 HOT 1
- RuntimeError HOT 3
- the change of gen_loss during training HOT 1
- RuntimeError
- RuntimeError HOT 2
- About the decreasing of loss HOT 1
- Can not reproduce the results HOT 12
- Training can get stuck HOT 6
- Inferior results trained from scratch HOT 7
- RuntimeeError HOT 1
- Can not reproduce the results HOT 3
- Training GPU requirements
- File "pesq/cypesq.pyx", line 1, in init cypesq ImportError: numpy.core.multiarray failed to import (auto-generated because you didn't call 'numpy.import_array()' after cimporting numpy; use '<void>numpy._import_array' to disable if you are certain you don't need it)
- File "/anaconda3/envs/cmg/lib/python3.9/site-packages/torch/nn/parallel/distributed.py", line 578, in __init__ dist._verify_model_across_ranks(self.process_group, parameters) RuntimeError: NCCL error in: ../torch/csrc/distributed/c10d/ProcessGroupNCCL.cpp:957, invalid usage, NCCL version 21.0.3 ncclInvalidUsage: This usually reflects invalid usage of NCCL library (such as too many async ops, too many collectives at once, mixing streams in a group, etc). HOT 2
- How do you resample to 16000?
- 时域Loss计算疑惑
- the training speed confusion
- My server has a 3090, but reports that I don't have a gpu HOT 1
- Test set requirements when training
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 cmgan.