STT

Creator

Creator

Seonglae Cho

Created

Created

2022 Jun 21 15:22

Editor

Editor

Seonglae Cho

Edited

Edited

2026 Oct 1 17:52

Refs

Refs

AI Transcription

Speech to Text, Speech Recognition, ASR(Automatic SR)

Key properties

Multilingual

Multi speaker diarization

Character level timestamps

STT Tools

ElevenLabs Scribe

Transcription AI

Canary 1b flash

STT Benchmarks

Common Voice

talkify-latency-bench

tornikegomareli • Updated 2026 Aug 17 14:7

speech-to-text recognition (ASR)

ASR Models

Unified Speech Recognition

Leaderboard

https://huggingface.co/spaces/hf-audio/open_asr_leaderboard

NVSpeech: Paralinguistic Vocalizations

https://arxiv.org/pdf/2508.04195

Data-Efficient On-Policy Distillation for Automatic Speech Recognition

Building competitive automatic speech recognition (ASR) models usually requires large-scale au- dio supervision, which makes reproduction and specialization expensive. We study Ark-ASR, a 0.6B-...

https://arxiv.org/abs/2605.28139

Multi-speaker separation

**Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization**

A Blog post by NVIDIA on Hugging Face

https://huggingface.co/blog/nvidia/nemotron-diarization

**Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization**

Backlinks

Voice AI Conformer

Recommendations

///////