hi, i have been going through the code and paper to get a thorough understanding of th

n_wins about nisqa HOT 2 CLOSED

gabrielmittag commented on June 13, 2024

n_wins

from nisqa.

Comments (2)

gabrielmittag commented on June 13, 2024 1

n_wins is the number of spectrogram segments/windows, which depends on the duration of the input speech sample and the hop size. It comes from this function:

NISQA/nisqa/NISQA_lib.py

Line 2239 in 47d8fea

def segment_specs(file_path, x, seg_length, seg_hop=1, max_length=None):

Basically, it is needed to make the model work with speech signals of different durations. You could also download the speech corpus and run the example scripts to get a better understanding of it.

from nisqa.

adam-sabra commented on June 13, 2024

thank you Gabriel

from nisqa.

Related Issues (20)

RuntimeError: Could not infer dtype of numpy.float32 HOT 10
Using NISQA as a loss function HOT 2
NISQA Corpus download issue HOT 1
Continuous metrics? HOT 4
TTS naturalness prediction based on which model
Could you tell me if the MOS rating is objective or subjective? HOT 4
Full Reference or No Reference When Subjectively Rating a Speech HOT 1
upper bound and larger bound inconsistent with step sign HOT 1
Audio input requirements HOT 2
pip package HOT 4
CDUA device does not load the model HOT 2
Interpertation of Different metrics HOT 1
The predict result seems not reliable HOT 3
License
upper bound and larger bound inconsistent with step sign
It seams slowly because of some functions running on CPU
max window length error for most audio files HOT 1
Utilizing finetuned weights
mos_pred预测分数有些奇怪
MOS prediction during runtime

n_wins about nisqa HOT 2 CLOSED

Comments (2)

Related Issues (20)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent