Skip to content
GitLab
Explore
Sign in
Register
Primary navigation
Search or go to…
Project
R
rnnoise
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Container Registry
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Terms and privacy
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Xiph.Org
rnnoise
Graph
1e7cbfefaa71c4dbc1c19ac6b3eabd7343b51902
Select Git revision
Branches
14
0.1.x
exp_fgnoise2
exp_model_load1
exp_newfeat5
exp_newfeat6
exp_newfeat8
exp_rir1
exp_rtcd1
gitlab-ci-mingw
issue-1
main
default
master
model-download-separate
upgrade1
Tags
3
v0.2
v0.1.1
v0.1
17 results
You can move around the graph by using the arrow keys.
Begin with the selected commit
Created with Raphaël 2.2.0
22
Feb
8
5
1
30
Jan
1
24
Aug
18
17
11
10
20
May
15
Apr
14
13
12
11
10
9
8
5
4
2
1
26
Mar
25
23
22
12
Mar
22
Jan
18
28
Jun
29
May
17
Oct
4
20
Sep
17
15
14
13
8
2
1
20
Aug
18
17
16
15
14
8
7
5
4
3
1
28
Jul
26
24
23
22
21
20
Remove outdated TRAINING-README
main
main
Added gitlab CI check for mingw/Windows build.
gitlab-ci-mingw
gitlab-ci-mingw
Made model downloading optional in autogen.sh using a --no-download option.
model-download-…
model-download-separate
List all export library symbols at the end of the build.
Fix -Wstrict-prototypes
m4: fix -Wstrict-protoypes
In rnnoise_init(), use rnnoise_get_size() for size of zeroed struct
issue-1
issue-1
Added gitlab CI script building with GCC and clang with a few configure options.
Augmentation/loss tuning, adding more noise data
Fix VAD fading bug
Fix typo "mix us data" to "mix of data"
Update training instructions
Add skip connections
Add sparse option, loss tuning
Minor tweaks to augmentation
Better signal/noise normalization
New models with updated augmentation
exp_fgnoise2
exp_fgnoise2
Consider energy changes in gain decay cap
Augment with saturation and quantization
Add Viterbi-based VAD for training
Tuning noise augmentation
Randomize filter based on pole/zero location
Augmentation using foreground noise
Added sha256 check for downloaded data
Fix compilation errors.
Add "little" model
v0.2
v0.2
Updating copyright notices
Adding more ways to load model
Add missing file
Script for shrinking C models
Updated README
Reviving model loading based on Opus code
Initial sparse matrix support copied from Opus
Adding one extra frame of delay
Noise data
Forgot weight dumping script
Forgot weight dumping script
exp_model_load1
exp_model_load1
Reviving model loading based on Opus code
Initial sparse matrix support copied from Opus
Adding one extra frame of delay
Loading