Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
multilingual_librispeech
Datasets & benchmarksHugging Face dataset by facebook
facebook/multilingual_librispeech -
flight-booking-screen-recording
Datasets & benchmarksHugging Face dataset by HumynLabs
HumynLabs/flight-booking-screen-recording -
peoples_speech
Datasets & benchmarksHugging Face dataset by MLCommons
MLCommons/peoples_speech -
Vaani
Datasets & benchmarksHugging Face dataset by ARTPARK-IISc
ARTPARK-IISc/Vaani -
Omni-SafetyBench
Datasets & benchmarks[ACM MM 2026 Oral] Code for paper "Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models".
git clone https://github.com/THU-BPM/Omni-SafetyBench.git -
Audio and speech made 11 of 59 named model launches since 6 Jul 2026, from 6 labs. In the.
-
Qwen: Qwen3.8 Omni Flash
ModelsQwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...
qwen/qwen3.8-omni-flash
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.