audio

Using this open-source model in production? Consider switching to pyannoteAI for better and faster o

Whisper small.en model for CTranslate2 This repository contains the conversion of distil-whisper/dis

Whisper medium.en model for CTranslate2 This repository contains the conversion of distil-whisper/di

Whisper distil-large-v2 model for CTranslate2 This repository contains the conversion of distil-whis

Whisper large-v2 model for CTranslate2 This repository contains the conversion of openai/whisper-lar

Whisper large-v1 model for CTranslate2 This repository contains the conversion of openai/whisper-lar

Whisper medium model for CTranslate2 This repository contains the conversion of openai/whisper-mediu

Whisper medium.en model for CTranslate2 This repository contains the conversion of openai/whisper-me

Whisper small.en model for CTranslate2 This repository contains the conversion of openai/whisper-sma

Whisper base model for CTranslate2 This repository contains the conversion of openai/whisper-base to

Whisper base.en model for CTranslate2 This repository contains the conversion of openai/whisper-base

Whisper tiny model for CTranslate2 This repository contains the conversion of openai/whisper-tiny to

Whisper tiny.en model for CTranslate2 This repository contains the conversion of openai/whisper-tiny

主要改动 这个模型是mossformer2，原来是一个说话人分离模型，在训练过程中，发现模型在说话人分离的同时具备很强的降噪效果，现在把降噪模型分离出来。 建议使用GPU进行推理，经过测试，GPU的推

主要改动 这个模型是mossformer2，2说话人，支持单声道，16k音频，同时发现模型在说话人分离的同时具备很强的降噪效果。 建议使用GPU进行推理，经过测试，GPU的推理速度是CPU的数十倍。

MARS5: A novel speech model for insane prosody. This is the repo for the MARS5 English speech model

模型介绍 Highlights 模型为Paraformer语音识别-中文-通用-16k-离线-large-热词版的torchscript导出版本，可以直接用来做生产部署，一键部署教程（点击此处） Mo

模型介绍 Highlights 模型为Paraformer语音识别-中文-通用-16k-离线-large-长音频版的torchscript导出版本，可以直接用来做生产部署，一键部署教程（点击此处） M

Paraformer-large-onnx模型介绍 Highlights 模型为Paraformer-large的torchscript导出版本，可以直接用来做生产部署，一键部署教程（点击此处） Mo

注意事项 本模型所用头像，形象，语音等等的所有权均归米哈游所有。只可用于二次创作。不得创作任何违反法律法规的内容，不得用于任何商业用途，不得二次配布。如有滥用行为，该模型将永久停止公开； 发视频请注