전체 검색
AI 모델 84761
- mms-tts-stp↗
facebook
- drama-3-int4↗
fishaudio
**The smallest working Drama 3.** Unofficial int4 quantization of fishaudio/drama-3 — Fish Audio's 35B (3B active) multi-speaker TTS model — with **real eval numbers** and one-command serving through SGLang Omni. The two checkpoints were compared on one H200 with the default SGLang Omni server settings: the 1,088 Seed-TTS English prompts, each cloning the voice of its own reference clip, sent as non-streaming requests at concurrency 8. WER is computed on the generated audio transcribed by Qwen3-ASR-1.7B. The int4 checkpoint is about 8% slower per request and its WER stays at the FP8 level: the gap between the two is about as large as the run-to-run spread of one checkpoint (a second FP8 run measured 1.365 s mean latency and 2.02% WER).
- multiberts-seed_24↗
Google
- owlvit-large-patch14↗
Google
The OWL-ViT (short for Vision Transformer for Open-World Localization) was proposed in Simple Open-Vocabulary Object Detection with Vision Transformers by Matthias Minderer, Alexey Gritsenko, Austin Stone, Maxim Neumann, Dirk Weissenborn, Alexey Dosovitskiy, Aravindh Mahendran, Anurag Arnab, Mostafa Dehghani, Zhuoran Shen, Xiao Wang, Xiaohua Zhai, Thomas Kipf, and Neil Houlsby. OWL-ViT is a zero-shot text-conditioned object detection model that can be used to query an image with one or multiple text queries. OWL-ViT uses CLIP as its multi-modal backbone, with a ViT-like Transformer to get visual features and a causal language model to get the text features. To use CLIP for detection, OWL-ViT removes the final token pooling layer of the vision model and attaches a lightweight classification and box head to each transformer output token. Open-vocabulary classification is enabled by replacing the fixed classification layer weights with the class-name embeddings obtained from the text model. The authors first train CLIP from scratch and fine-tune it end-to-end with the classification and box heads on standard detection datasets using a bipartite matching loss. One or multiple text queries per image can be used to perform zero-shot text-conditioned object detection. The model uses a CLIP backbone with a ViT-L/14 Transformer architecture as an image encoder and uses a masked self-attention Transformer as a text encoder. These encoders are trained to maximize the similarity of (image, text) pairs via a contrastive loss. The CLIP backbone is trained from scratch and fine-tuned together with the box and class prediction heads with an object detection objective.
- pix2struct-textcaps-base↗
Google
- shieldgemma-27b↗
Google
- t5-efficient-small-kv16↗
Google
- spell-sft↗
Grizzlykw
- Qwen3-4B-Instruct-2507-20250808-233922-0-i1-GGUF↗
guray16
- granite-speech-3.3-8b↗
ibm-granite
**Model Summary:** Granite-speech-3.3-8b is a compact and efficient speech-language model, specifically designed for automatic speech recognition (ASR) and automatic speech translation (AST). Granite-speech-3.3-8b uses a two-pass design, unlike integrated models that combine speech and language into a single pass. Initial calls to granite-speech-3.3-8b will transcribe audio files into text. To process the transcribed text using the underlying Granite language model, users must make a second call as each step must be explicitly initiated. The model was trained on a collection of public corpora comprising diverse datasets for ASR and AST as well as synthetic datasets tailored to support the speech translation task. Granite-speech-3.3-8b was trained by modality aligning granite-3.3-8b-instruct (https://huggingface.co/ibm-granite/granite-3.3-8b-instruct) to speech on publicly available open source corpora containing audio inputs and text targets. We evaluated granite-speech-3.3-8b revision 3.3.2 alongside other speech-language models in the less than 8b parameter range as well as dedicated ASR and AST systems on standard benchmarks. The evaluation spanned multiple public benchmarks, with particular emphasis on English ASR tasks while also including multilingual ASR and AST for X-En and En-X translations.
