-
Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models,
arXiv, 2501.02832
, arxiv, pdf, cication: -1Syed Abdul Gaffar Shakhadri, Kruthika KR, Kartik Basavaraj Angadi
-
🌟 A Comparative Study of Discrete Speech Tokens for Semantic-Related Tasks with Large Language Models,
arXiv, 2411.08742
, arxiv, pdf, cication: -1Dingdong Wang, Mingyu Cui, Dongchao Yang, ..., Xueyuan Chen, Helen Meng
-
Moonshine: Speech Recognition for Live Transcription and Voice Commands,
arXiv, 2410.15608
, arxiv, pdf, cication: -1Nat Jeffries, Evan King, Manjunath Kudlur, ..., James Wang, Pete Warden · (moonshine - usefulsensors)
-
transformers.js-examples - huggingface
-
whisper-ner - aiola-lab
· (arxiv)
-
CrisperWhisper - nyrahealth
· (huggingface)
-
Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context,
arXiv, 2309.08105
, arxiv, pdf, cication: -1Wei Kang, Xiaoyu Yang, Zengwei Yao, ..., Long Lin, Daniel Povey
-
CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions,
arXiv, 2408.16589
, arxiv, pdf, cication: -1Laurin Wagner, Bernhard Thallinger, Mario Zusag · (huggingface)