Kotoba Technologies

company

Verified

https://kotoba.tech

AI & ML interests

Building Speech-to-Speech Foundation Models

Recent Activity

kamahori authored a paper 27 days ago

VoxServe: Streaming-Centric Serving System for Speech Language Models

kamahori submitted a paper 28 days ago

VoxServe: Streaming-Centric Serving System for Speech Language Models

kamahori authored a paper 5 months ago

DualTune: Decoupled Fine-Tuning for On-Device Agentic Systems

View all activity

authored a paper 27 days ago

VoxServe: Streaming-Centric Serving System for Speech Language Models

Paper • 2602.00269 • Published Jan 30 • 6

submitted a paper to Daily Papers 28 days ago

VoxServe: Streaming-Centric Serving System for Speech Language Models

Paper • 2602.00269 • Published Jan 30 • 6

authored a paper 5 months ago

DualTune: Decoupled Fine-Tuning for On-Device Agentic Systems

Paper • 2510.00229 • Published Sep 30, 2025 • 1

hpprc

authored a paper 6 months ago

Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddings

Paper • 2506.01435 • Published Jun 2, 2025

authored a paper 8 months ago

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices

Paper • 2506.17538 • Published Jun 21, 2025 • 7

updated 2 Spaces 10 months ago

JA STS Arena

Vote on the top Japanese Speech-to-Speech models!

Seamless M4T v2

published 2 Spaces 10 months ago

Seamless M4T v2

JA STS Arena

Vote on the top Japanese Speech-to-Speech models!

updated a Space 10 months ago

JA TTS Arena

Vote on the top Japanese TTS models!

authored a paper about 1 year ago

TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval

Paper • 2502.20969 • Published Feb 28, 2025 • 11

authored a paper about 1 year ago

LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation

Paper • 2502.20583 • Published Feb 27, 2025 • 13

authored a paper about 1 year ago

LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation

Paper • 2502.20583 • Published Feb 27, 2025 • 13

published 2 datasets about 1 year ago

kotoba-tech/kotoba-whisper-eval

Viewer • Updated Apr 21, 2024 • 4 • 10

kotoba-tech/seamless-align-enA-jaA-tmp

Updated May 23, 2024 • 5

updated a Space over 1 year ago

JA TTS Arena

Vote on the top Japanese TTS models!

updated a Space over 1 year ago

JA TTS Arena

Vote on the top Japanese TTS models!

updated a Space over 1 year ago

Kotoba Whisper Diarization Demo

Transcribe and diarize audio files or microphone input

updated 2 models over 1 year ago

kotoba-tech/kotoba-whisper-v2.2

Automatic Speech Recognition • 0.8B • Updated Oct 23, 2024 • 18.2k • 95

kotoba-tech/kotoba-whisper-v2.1

Automatic Speech Recognition • 0.8B • Updated Oct 23, 2024 • 2.63k • 19