tiantiaf/wavlm-large-age-sex
Audio Classification • 0.3B • Updated • 1.75k • 11
Vox-Profile
This collection includes the implementation of models described in the Vox-Profile benchmark. (https://arxiv.org/pdf/2505.14648).
-
-
tiantiaf/whisper-large-v3-msp-podcast-emotion
Audio Classification • 2B • Updated • 2.2k • 6 -
tiantiaf/whisper-large-v3-broad-accent
Audio Classification • 2B • Updated • 58 • 1 -
tiantiaf/whisper-large-v3-narrow-accent
Audio Classification • 2B • Updated • 208 • 5 -
tiantiaf/whisper-large-v3-msp-podcast-emotion-dim
Audio Classification • 2B • Updated • 2.58k • 4 -
tiantiaf/whisper-large-v3-voice-quality
Audio Classification • 2B • Updated • 99 • 4 -
tiantiaf/whisper-large-v3-speech-flow
Audio Classification • 2B • Updated • 32 • 3 -
tiantiaf/wavlm-large-categorical-emotion
Audio Classification • 0.3B • Updated • 335 • 4 -
tiantiaf/wavlm-large-broader-accent
Audio Classification • 0.3B • Updated • 281 • 2 -
tiantiaf/wavlm-large-speech-flow
Audio Classification • 0.3B • Updated • 324 • 1 -
tiantiaf/wavlm-large-narrow-accent
Audio Classification • 0.3B • Updated • 159 • 1 -
tiantiaf/wavlm-large-voice-quality
Audio Classification • 0.3B • Updated • 352 • 4 -
tiantiaf/wavlm-large-msp-podcast-emotion-dim
Audio Classification • 0.3B • Updated • 963 • 5 -
Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits
Paper • 2505.14648 • Published • 10