Seich
/
mayavoz
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #28 from shahules786/dev 

Update Readme
This commit is contained in:
Shahul ES 2022-11-24 16:18:45 +05:30 committed by GitHub
parent dd0b060e09 763ea60a52
commit a47b93b699
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 20 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
README.md
View File

@ -10,7 +10,7 @@
mayavoz is a Pytorch-based opensource toolkit for speech enhancement. It is designed to save time for audio researchers. Is provides easy to use pretrained audio enhancement models and facilitates highly customisable model training. mayavoz is a Pytorch-based opensource toolkit for speech enhancement. It is designed to save time for audio researchers. Is provides easy to use pretrained audio enhancement models and facilitates highly customisable model training.
| **[Quick Start](#quick-start-fire)** | **[Installation](#installation)** | **[Tutorials](https://github.com/shahules786/enhancer/tree/main/notebooks)** | **[Available Recipes](#recipes)** | **[Demo]()** | **[Quick Start](#quick-start-fire)** | **[Installation](#installation)** | **[Tutorials](https://github.com/shahules786/enhancer/tree/main/notebooks)** | **[Available Recipes](#recipes)** | **[Demo](#demo)**
## Key features :key: ## Key features :key:
* Various pretrained models nicely integrated with huggingface :hugs: that users can select and use without any hastle. * Various pretrained models nicely integrated with huggingface :hugs: that users can select and use without any hastle.
@ -18,12 +18,21 @@ mayavoz is a Pytorch-based opensource toolkit for speech enhancement. It is desi
* :magic_wand: A command line tool that facilitates training of highly customisable speech enhacement models from the terminal itself! * :magic_wand: A command line tool that facilitates training of highly customisable speech enhacement models from the terminal itself!
* :zap: Supports multi-gpu training integrated with Pytorch Lightning. * :zap: Supports multi-gpu training integrated with Pytorch Lightning.
## Demo
Noisy audio followed by enhanced audio.
https://user-images.githubusercontent.com/25312635/203756185-737557f4-6e21-4146-aa2c-95da69d0de4c.mp4
## Quick Start :fire: ## Quick Start :fire:
``` python ``` python
from mayavoz.models import Mayamodel from mayavoz.models import Mayamodel
model = Mayamodel.from_pretrained("shahules786/mayavoz-waveunet-valentini-28spk") model = Mayamodel.from_pretrained("shahules786/mayavoz-waveunet-valentini-28spk")
model("noisy_audio.wav") model.enhance("noisy_audio.wav")
``` ```
## Recipes ## Recipes

9
tests/test_inference.py
View File

@ -27,3 +27,12 @@ def test_aggregate():
data=rand, window_size=100, total_frames=1000, step_size=100 data=rand, window_size=100, total_frames=1000, step_size=100
) )
assert agg_rand.shape[-1] == 1000 assert agg_rand.shape[-1] == 1000
def test_pretrained():
from mayavoz.models import Mayamodel
model = Mayamodel.from_pretrained(
"shahules786/mayavoz-waveunet-valentini-28spk"
)
_ = model.enhance("tests/data/vctk/clean_testset_wav/p257_166.wav")