voc2vec is a foundation model specifically designed for non-verbal human data.
Alkis Koudounas
alkiskoudounas
AI & ML interests
Speech and Audio Processing | Multimodal Understanding | Trustworthy and Responsible AI
Recent Activity
published a bucket 12 days ago
alkiskoudounas/speech-ebt-tracking-bucket updated a model 7 months ago
alkiskoudounas/mt5-xl-mugec-lora-10best published a model 7 months ago
alkiskoudounas/mt5-xl-mugec-lora-10bestOrganizations
SSL models fine-tuned for the spoken intent classification task
-
alkiskoudounas/xls-r-53-it-italic-speaker
Audio Classification • Updated • 10 -
alkiskoudounas/xls-r-128-italic-speaker
Audio Classification • 0.3B • Updated • 11 -
alkiskoudounas/xls-r-128-italic-massive
Audio Classification • Updated • 11 -
alkiskoudounas/xls-r-128-italic-noisy
Audio Classification • Updated • 11
SSL models pre-trained on AudioSet
Models trained and released for the paper: "Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding
-
alkiskoudounas/hubert-base-fsc-gold
Audio Classification • 94.6M • Updated • 12 -
alkiskoudounas/wav2vec2-base-fsc-gold
Audio Classification • 94.6M • Updated • 8 -
alkiskoudounas/wav2vec2-base-unslurp-gold
Audio Classification • 94.6M • Updated • 8 -
alkiskoudounas/hubert-base-unslurp-gold
Audio Classification • 94.6M • Updated • 8
voc2vec is a foundation model specifically designed for non-verbal human data.
SSL models pre-trained on AudioSet
SSL models fine-tuned for the spoken intent classification task
-
alkiskoudounas/xls-r-53-it-italic-speaker
Audio Classification • Updated • 10 -
alkiskoudounas/xls-r-128-italic-speaker
Audio Classification • 0.3B • Updated • 11 -
alkiskoudounas/xls-r-128-italic-massive
Audio Classification • Updated • 11 -
alkiskoudounas/xls-r-128-italic-noisy
Audio Classification • Updated • 11
Models trained and released for the paper: "Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding
-
alkiskoudounas/hubert-base-fsc-gold
Audio Classification • 94.6M • Updated • 12 -
alkiskoudounas/wav2vec2-base-fsc-gold
Audio Classification • 94.6M • Updated • 8 -
alkiskoudounas/wav2vec2-base-unslurp-gold
Audio Classification • 94.6M • Updated • 8 -
alkiskoudounas/hubert-base-unslurp-gold
Audio Classification • 94.6M • Updated • 8