Recent video large language models (Video LLMs) often depend on costly human
annotations or proprietary model APIs (per esempio., GPT-4o) to produce training data,
which limits their training at scale. In questo documento, we explore large-scale
training for Video LLM with cheap automatic speech recognition (ASR)
transcripts. Nello specifico, we propose a novel streaming training approach that
densely interleaves the ASR words and video frames according to their
timestamps. Compared to previous studies in vision-language representation with
ASR, our method naturally fits the streaming characteristics of ASR, thus
enabling the model to learn temporally-aligned, fine-grained vision-language
modeling. To support the training algorithm, we introduce a data production
pipeline to process YouTube videos and their closed captions (CC, same as ASR),
resulting in Live-CC-5M dataset for pre-training and Live-WhisperX-526K dataset
for high-quality supervised fine-tuning (SFT). Remarkably, even without SFT,
the ASR-only pre-trained LiveCC-7B-Base model demonstrates competitive general
video QA performance and exhibits a new capability in real-time video
commentary. To evaluate this, we carefully design a new LiveSports-3K
segno di riferimento, using LLM-as-a-judge to measure the free-form commentary.
Experiments show our final LiveCC-7B-Instruct model can surpass advanced 72B
modelli (Qwen2.5-VL-72B-Instruct, LLaVA-Video-72B) in commentary quality even
working in a real-time mode. Nel frattempo, it achieves state-of-the-art results at
the 7B/8B scale on popular video QA benchmarks such as VideoMME and OVOBench,
demonstrating the broad generalizability of our approach. All resources of this
paper have been released at https://showlab.github.io/livecc.

Questo articolo esplora i giri e le loro implicazioni.

Scarica PDF: