qi-hua / async_cosyvoiceLinks
使用vllm加速cosyvoice2的推理
☆467Updated 8 months ago
Alternatives and similar repositories for async_cosyvoice
Users that are interested in async_cosyvoice are comparing it to the libraries listed below
Sorting:
- Pseudo Streaming SenseVoice with Hotwords☆419Updated 10 months ago
- Added vLLM support to IndexTTS for faster inference.☆998Updated 2 months ago
- ☆204Updated last year
- Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.☆684Updated last week
- KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-…☆525Updated 2 years ago
- Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching☆764Updated last month
- Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.☆690Updated last month
- 基于SparkTTS、OrpheusTTS等模型，提供高质量中文语音合成与声音克隆服务。☆579Updated 7 months ago
- Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR be…☆1,713Updated 3 weeks ago
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆313Updated 3 weeks ago
- ☆377Updated last year
- Text Normalization & Inverse Text Normalization☆716Updated last month
- An Open-Sourced LLM-empowered Foundation TTS System☆892Updated 3 months ago
- OSUM & OSUM-EChat, open speech understanding model and empathetic spoken chatbot based on it, open-sourced by ASLP@NPU.☆469Updated last month
- Bert-VITS2项目bug多且教程不友好。本proj尽可能修复了Bert-vits2项目的bug，并且可一键启动训练。仅需50条目标说话人语音，获得稳定、快速的TTS模型。☆65Updated 4 months ago
- 基于标贝数据继续训练，同时对原本的FastSpeech2模型做了改进，引入了韵律表征以及韵律预测模块，使中文发音更生动且富有节奏☆275Updated 2 years ago
- ☆145Updated 2 years ago
- API and websocket server for sensevoice. It has inherited some enhanced features, such as VAD detection, real-time streaming recognition,…☆538Updated last year
- MOSS-TTSD is a spoken dialogue generation model that enables expressive dialogue speech synthesis in both Chinese and English, supporting…☆1,074Updated last month
- ☆823Updated last year
- 基于FunASR实现语音识别，包含常规版和ONNX版(推荐)。☆47Updated last year
- Port of Funasr's Sense-voice model in C/C++☆508Updated 3 weeks ago
- Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation…☆1,300Updated 3 months ago
- F5-TTS 推理加速，速度提升约4倍！☆121Updated last year
- MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction mode…☆219Updated last year
- 端到端语音唤醒工具箱，从模型训练到模型推理。☆149Updated 5 months ago
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆92Updated last month
- 一个用于CosyVoice的api接口项目☆332Updated 4 months ago
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆677Updated 3 months ago
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆412Updated last month