Maximilian Schmitt
audmax
·
AI & ML interests
Speech, Audio, Music, LLMs
Recent Activity
new activity
7 months ago
audeering/wav2vec2-large-robust-12-ft-emotion-msp-dim:How to accelerate emotion extract speed?
Organizations
audmax's activity
Inferences API Results: Similar Values for Arosal, Valence, and Dominance
5
#11 opened 3 months ago
by
shivamisb
How to accelerate emotion extract speed?
1
#10 opened 7 months ago
by
kdrkdrkdr
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1671034220324-634bfbcb002a36a2bdb54ae1.png)
Explnation on using the ONNX model
2
#5 opened 10 months ago
by
yovelcohen1
Some weights not initialized : harmless warning
1
#4 opened about 1 year ago
by
mpariente
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1607369599055-5fa5b2a5a13e063b8b2b5f2f.jpeg)
Testing the Model with an Example Wav File
3
#1 opened almost 2 years ago
by
krugjo
Converting VAD into Ekman
1
#3 opened over 1 year ago
by
mirix
i need to verify this pretrained model on another datasets xith multiple wave file how to arrange the code
1
#7 opened about 1 year ago
by
messaoudi
Batched inference does not yield same results as individual sample inference
1
#8 opened 11 months ago
by
ladhiet
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/-ij8v7Z38KaFlWd3O2Tas.jpeg)