Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
O LTX-2 abandona a abordagem de gerar vídeo e áudio separadamente: um transformer de duplo fluxo aprende ambos ao mesmo tempo, produzindo conteúdo audiovisual sincronizado de ponta.
arXiv:2606.25487v1 Announce Type: new Abstract: Almost every paper on LLM jailbreaks and prompt injection reports an attack-success rate (ASR), and that number is assigned not by people but by an automated judge: either a safety classifier trained for the task, or a general chat model prompted to grade. The judge is rarely checked. We check it. Using 596 human-labeled completions from the HarmBench classifier validation set, we compare the two judge families against human majority votes and then...
arXiv:2606.24889v1 Announce Type: new Abstract: Automatic speech recognition (ASR) systems, despite low overall word error rates, produce residual lexical errors that disproportionately affect semantically critical tokens such as named entities, negations, and sentiment-bearing words. These errors are often structured, arising from phonetic similarity rather than random noise, making naive token-level correction insufficient. We propose a structured ASR correction framework, that we call G-SPIN,...
arXiv:2606.25009v1 Announce Type: new Abstract: Ultrasound is a non-invasive, real-time, and cost-effective imaging technique widely used in clinical diagnosis. However, its diagnostic efficacy is often compromised by inherent speckle noise that degrades image quality and obscures underlying anatomical structures. Existing speckle reduction methods tend to over-smooth tissue boundaries and generalize poorly to heterogeneous noise levels. To address these limitations, we propose a Noise-Aware Bou...
arXiv:2606.25041v1 Announce Type: new Abstract: We present Wan-Streamer, a native-streaming, end-to-end interactive foundation model designed from the ground up for real-time, low-latency, full-duplex audio-visual interaction. Wan-Streamer seamlessly models language, audio, and video as both input and output within a single Transformer, where the sequence is represented as interleaved visual, audio, and text input tokens together with visual, audio, and text output tokens, coordinated by block-c...
arXiv:2606.25459v1 Announce Type: new Abstract: While self-supervised speech models have achieved strong performance across speech tasks, relatively little is known about how their internal phonetic representations behave under fine-grained dialect variation. Existing probing studies typically rely on curated corpora with manual phonetic annotations, limiting their applicability to naturally occurring dialect speech. We present a case study of articulatory feature representations in a Mandarin s...
arXiv:2606.24915v1 Announce Type: new Abstract: End-to-end automatic speech recognition systems frequently hallucinate rare entities and domain-specific terms, especially in low-resource languages. While retrieval-augmented generation frameworks can mitigate these errors using large language models, current architectures face significant challenges. They either rely on standard sparse retrieval that ignores phonetic misrecognitions or utilize heavyweight cross-modal embeddings that introduce hig...
arXiv:2606.25225v1 Announce Type: new Abstract: Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning. Since audio and visual streams naturally co-occur in video data, extending this success to jointly learn from both modalities is a natural next step, yet it remains challenging. Existing audio-visual self-supervised methods rely on modality-specific encoders and complex combinations of contrastive or reconstruction objectives,...
Multilingual safety and fairness benchmark for speech models reveals persistent vulnerabilities across languages and naturalistic conditions.
Modelo de síntese de voz em alta no Hugging Face — 86.1 mil downloads e 527 curtidas da comunidade.
Gradium released two real-time speech translation models, stt-translate and s2s-translate, covering English, French, German, Spanish, and Portuguese across 20 language pairs. The models collapse the standard three-model cascade into two, pairing single-pass transcription-and-translation with a Gradium TTS stage over one duplex WebSocket. Gradium reports a better accuracy-latency tradeoff than gpt-realtime-translate and gemini-3.5-live-translate, plus output voice selection and cloning. The post ...
Dataset com menos de mil exemplos — 634 downloads no Hugging Face. OmniVoice VI — Giọng Việt + SRT lồng tiếng Dataset chứa 6 giọng tiếng Việt và công cụ speak.