Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR
Paper
•
2409.15869
•
Published
Aviv Shamsian
AvivSham
AI & ML interests
None yet
Recent Activity
new activity
about 1 month ago
mradermacher/Orpheus-3B-pt-GGUF:voices
new activity
about 1 month ago
Gapeleon/Orpheus-3B-pt:voices
upvoted
a
paper
about 2 months ago
Drax: Speech Recognition with Discrete Flow Matching
Organizations
None yet
authored
7
papers
3 months ago
WhisperNER: Unified Open Named Entity and Speech Recognition
Paper
•
2409.08107
•
Published
Auxiliary Learning as an Asymmetric Bargaining Game
Paper
•
2301.13501
•
Published
Equivariant Architectures for Learning in Deep Weight Spaces
Paper
•
2301.12780
•
Published
LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading
Paper
•
2306.03258
•
Published
•
1
Data Augmentations in Deep Weight Spaces
Paper
•
2311.08851
•
Published
Beyond Transcription: Mechanistic Interpretability in ASR
Paper
•
2508.15882
•
Published
•
86