espnet/Bagpiper_PreTrain
Viewer • Updated • 32.3M • 454
AI & ML interests
voice-conversion speech-separation speech-enhancement speech-translation speech-synthesis speech-recognition spoken-language-understanding
Recent Activity
JinchuanTian
updated a
dataset about 15 hours ago
JinchuanTian
published a
dataset 2 days ago
app.py
#4 opened 14 days ago
by 
nathanjames
app.py
#5 opened 14 days ago
by nathanjames
RishabA
updated a
model 17 days ago
RishabA
published a
model 18 days ago
Post
206
Existing methods — GPTQ, AWQ, llama.cpp's k-quants — minimize empirical loss heuristically. None of them prove they are optimal in any information-theoretic sense. ICRB-Q builds a quantization scheme that is provably optimal via the Cramér-Rao lower bound (CRB): no unbiased estimator of a weight can have lower variance than [F(θ)]⁻¹, where F is the Fisher information matrix.
- 1 reply
vectominist
authored 2
papers 20 days ago
d3bach
authored 2
papers 26 days ago
cyhuang-tw
updated a
model about 1 month ago
cyhuang-tw
published a
model about 1 month ago
cjli
updated a
model about 2 months ago
Aniket-Tathe-08
updated a
model 2 months ago
Post
3283
Built a small site for tracking speech-to-speech, full-duplex, and audio foundation model work.
It covers models, benchmarks, datasets, and some blog posts to organize the landscape in one place.
Still early, but sharing in case it is useful:
https://www.fullduplex.ai/
If you spot missing entries or mistakes, I would really appreciate corrections.
It covers models, benchmarks, datasets, and some blog posts to organize the landscape in one place.
Still early, but sharing in case it is useful:
https://www.fullduplex.ai/
If you spot missing entries or mistakes, I would really appreciate corrections.
- 2 replies
Aniket-Tathe-08
published a
model 2 months ago
sanchit-gandhi
authored a
paper 3 months ago
cjli
authored a
paper 3 months ago
Add Open ASR Leaderboard evaluation results
1
#4 opened 3 months ago
by 
SaylorTwift