VoxCPM is an innovative tokenizer-free end-to-end text-to-speech (TTS) system that overcomes the limitations of discrete tokenization by modeling speech in a continuous space. It has two core capabilities: context-aware speech generation and realistic zero-shot voice cloning. It can automatically adjust the prosody and style according to the text content and clone the speaker's timbre, accent, and emotion with just a short reference audio.

Audio ProcessingSafetensorsMultiple Languages

A static quantized version of UME-R1-7B, supporting multiple tasks such as sentence similarity, embedding, zero-shot image classification, and video text-to-text. It offers various quantization types to meet different needs, from the lightweight Q2_K to the high-quality Q8_0 version.

MultimodalTransformersEnglish

Chronos-2 is a time series foundation model with 120 million parameters, supporting zero-shot prediction. It supports univariate, multivariate, and covariate-aware tasks within a single architecture, achieving state-of-the-art accuracy in zero-shot prediction across multiple benchmarks, and has extremely high inference efficiency.

Scientific ComputingSafetensors

Kairos-10M is a time series foundation model designed for cross-domain zero-shot prediction, with approximately 10 million parameters. It can handle heterogeneous time series data with different information densities and achieve strong generalization ability across different domains without fine-tuning.

Scientific ComputingTransformers

Kairos-50M is a time series foundation model with 50 million parameters, specifically designed for zero-shot prediction across different domains. It uses adaptive word segmentation and position encoding techniques to handle heterogeneous time series data with different information densities and can achieve strong generalization ability across different domains without fine-tuning.

Scientific ComputingTransformers

Zonos-v0.1 is a leading open-source text-to-speech (TTS) model, trained on over 200,000 hours of multilingual speech data, comparable in expressiveness and quality to top TTS providers. It supports zero-shot voice cloning, multilingual synthesis, and fine-grained audio control.

Audio ProcessingOnnx

MGM-Omni-TTS-2B is the voice generation component of the MGM-Omni full-featured chatbot, specifically designed for text-to-speech conversion. It supports zero-shot voice cloning in Chinese and English, can generate smooth and natural voices longer than 10 minutes, and achieve efficient streaming audio generation.

MultimodalTransformersMultiple Languages

MGM-Omni-7B is a full-modal chatbot capable of processing text, image, video, and speech inputs and generating text and speech responses. It has the ability to understand and generate long speeches and also supports zero-shot speech cloning in both Chinese and English.

MultimodalTransformersMultiple Languages

MetaCLIP 2 (worldwide) is a multilingual zero-shot image classification model based on the Transformer architecture. It supports visual language understanding tasks globally and can classify images without training.

MultimodalTransformersOther

GLiClass is an efficient zero-shot classifier with performance comparable to cross-encoders but higher computational efficiency, suitable for multi-task scenarios.

Natural Language ProcessingSafetensorsOther

GLiClass is an efficient zero-shot classifier with performance comparable to cross-encoders but higher computational efficiency, supporting multilingual text classification tasks.

Natural Language ProcessingSafetensors

GLiClass is an efficient zero-shot classifier inspired by GLiNER, capable of completing classification tasks in a single forward pass, combining the performance of a cross-encoder with higher computational efficiency.

Natural Language ProcessingSafetensorsOther

DermLIP is a dermatological vision-language model trained on the Derm1M dataset. It uses a CLIP-style contrastive learning method and is specifically optimized for dermatological images and texts, supporting various application scenarios such as zero-shot classification and few-shot learning.

MultimodalTransformersEnglish

DermLIP is a vision-language model specifically designed for the field of dermatology, trained on the largest dermatology image-text corpus, Derm1M. This model adopts a CLIP-style architecture and can perform various dermatology-related tasks, including zero-shot classification, few-shot learning, cross-modal retrieval, and concept annotation.

MultimodalTransformersEnglish

A zero-shot skin disease assessment model based on vision-language pre-training technology, integrating multi-faceted knowledge enhancement to provide an effective tool for skin disease research and diagnosis.

MultimodalOpenclip

A zero-shot classification model based on the Transformers architecture that can classify text without fine-tuning

Natural Language ProcessingTransformers

This is a transformers model for zero-shot classification tasks, which can classify text without a large amount of labeled data.

Natural Language ProcessingTransformers

Spark-TTS is an efficient text-to-speech system based on large language models (LLM), supporting bilingual synthesis in Chinese and English with zero-shot voice cloning.

Audio ProcessingSafetensorsMultiple Languages

Whisper is OpenAI's state-of-the-art automatic speech recognition (ASR) and speech translation model, trained on over 5 million hours of labeled data with strong zero-shot generalization capabilities. The Turbo version is a pruned and fine-tuned variant of the original, reducing decoder layers from 32 to 4, significantly improving speed with a slight quality trade-off.

Audio ProcessingTransformersMultiple Languages

Sundial is a series of generative time series foundation models capable of zero-shot inference for both deterministic and probabilistic forecasting.

Scientific ComputingSafetensors