Ming-UniAudio is an innovative unified speech framework that integrates speech understanding, generation, and editing functions into one. It uses a unified continuous speech tokenizer, which can effectively fuse semantic and acoustic features in an end-to-end model. It is the first system that can achieve general and free-form speech editing only through natural language instructions.

MultimodalSafetensors

Qwen2.5-Omni-3B-GGUF is an end-to-end multimodal model capable of perceiving various modal information such as text, images, audio, and video, and generating text and natural speech responses in a streaming manner.

MultimodalTransformersEnglish

Qwen2.5-Omni is an end-to-end multimodal model capable of perceiving various modalities such as text, images, audio, and video, and generating text and natural speech responses in a streaming manner.

MultimodalTransformersEnglish

Qwen2.5-Omni is an end-to-end multimodal model capable of perceiving multiple modalities including text, images, audio, and video, while generating text and natural speech responses in a streaming manner.

MultimodalTransformersEnglish

Qwen2.5-Omni is an end-to-end multimodal model capable of perceiving various modalities including text, images, audio, and video, while synchronously generating text and natural speech responses in a streaming manner.

MultimodalTransformersEnglish

EMOVA is an end-to-end omni-modal large language model that supports visual, auditory, and speech functions, capable of generating text and speech responses with emotional control.

MultimodalTransformersMultiple Languages

Qwen2.5-Omni is an end-to-end multimodal model capable of perceiving various modalities such as text, images, audio, and video, and generating text and natural speech responses in a streaming manner.

MultimodalTransformersEnglish

EMOVA is an end-to-end omni-modal large language model that supports visual, auditory, and speech capabilities, with emotional speech dialogue abilities.

MultimodalTransformersMultiple Languages

EMOVA is an end-to-end omnipotent modality large language model that supports vision, hearing, and speech functions, enabling multimodal understanding and generation without relying on external models.

MultimodalTransformersMultiple Languages

Typhoon 2-Audio Edition is an end-to-end speech-to-speech model architecture capable of processing audio, speech, and text inputs while simultaneously generating both text and speech outputs. The model is specifically optimized for Thai language while also supporting English.

MultimodalTransformersMultiple Languages

An end-to-end speaker diarization model based on the Sortformer architecture, which resolves permutation issues in diarization by ordering speech segments according to speaker arrival time, supporting recognition of up to 4 speakers.

Audio ProcessingPytorch

This is an end-to-end speaker segmentation model for voice activity detection, overlap speech detection, and resegmentation tasks.

Audio ProcessingTensorboard

FlowMirror is an end-to-end speech model developed by Zhejiang Jingzhunxue AI Lab, supporting tasks such as voice dialogue, ASR, and TTS, with a focus on educational applications

MultimodalTransformers

DiVA Llama 3 is an end-to-end voice assistant model capable of processing both speech and text inputs, trained using distillation loss.

MultimodalTransformers

VITS is an end-to-end text-to-speech model based on adversarial learning and conditional variational autoencoder, supporting Chinese speech synthesis.

Audio ProcessingTransformersChinese

Nue ASR is an end-to-end Japanese speech recognition model that integrates pre-trained speech and language models, offering high accuracy and fast recognition speed.

Audio ProcessingTransformersMultiple Languages

Marshallese text-to-speech model developed by Meta, using VITS end-to-end architecture to support high-quality speech synthesis

Audio ProcessingTransformers

Mossi text-to-speech model developed by Meta, based on VITS architecture, supporting end-to-end speech synthesis

Audio ProcessingTransformers

Catalan text-to-speech model developed by Meta, utilizing the VITS end-to-end architecture for high-quality speech synthesis

Audio ProcessingTransformers

A Kuwaa language (blh) text-to-speech model developed by Meta, which is part of the Massive Multilingual Speech project and uses the VITS end-to-end speech synthesis architecture.

Audio ProcessingTransformers