From TOWER to SPIRE: Adding the Speech Modality to a Text-Only LLM
Paper
•
2503.10620
•
Published
•
7
Marcely Zanon Boito
mzboito
AI & ML interests
speech processing, speech translation, NLProc, low-resource processing
Recent Activity
new activity
13 days ago
naver/multilingual-distilwhisper-10k:Adding `safetensors` variant of this model
upvoted
an
article
about 1 month ago
EuroLLM-9B
new activity
about 2 months ago
naver/mHuBERT-147-ASR-fr:Adding `safetensors` variant of this model
Organizations
authored
a
paper
4 months ago
authored
5
papers
11 months ago
DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific Experts
Paper
•
2311.01070
•
Published
•
2
Speech Resources in the Tamasheq Language
Paper
•
2201.05051
•
Published
LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech
Paper
•
2309.05472
•
Published
A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems
Paper
•
2204.01397
•
Published
mHuBERT-147: A Compact Multilingual HuBERT Model
Paper
•
2406.06371
•
Published
•
7