qi-hua / async_cosyvoice
使用vllm加速cosyvoice2的推理
☆127Updated last week
Alternatives and similar repositories for async_cosyvoice:
Users that are interested in async_cosyvoice are comparing it to the libraries listed below
- ☆193Updated 6 months ago
- Pseudo Streaming SenseVoice with Hotwords☆233Updated 3 weeks ago
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English.☆94Updated 2 weeks ago
- Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice☆277Updated 2 months ago
- 端到端语音唤醒工具箱，从模型训练到模型推理。☆109Updated 6 months ago
- Unoffical implementation of Megatts2☆279Updated last year
- TTS appalication based on modelscope KAN-TTS☆43Updated 11 months ago
- 基于FunASR实现语音识别，包含常规版和ONNX版(推荐)。☆36Updated 5 months ago
- 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。☆52Updated 3 weeks ago
- TTSAudioNormalizer is a specialized tool for TTS data production, featuring descriptive statistical analysis of audio loudness and loud…☆93Updated 3 months ago
- MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction mode…☆199Updated 2 months ago
- Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction☆166Updated last month
- ☆111Updated last year
- OSUM: Open Speech Understanding Model, open-sourced by ASLP@NPU.☆346Updated 2 weeks ago
- FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music gener…☆392Updated last year
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆64Updated 3 months ago
- A enterprise-grade Voice Activity Detector from modelscope and funasr.☆88Updated last year
- Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.☆141Updated this week
- text to speech using autoregressive transformer and VITS☆236Updated last year
- An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System☆406Updated this week
- 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☆260Updated last year
- Paper, Code and Resources for Speech Language Model and End2End Speech Dialogue System.☆163Updated 4 months ago
- F5-TTS 推理加速，速度提升约4倍！☆64Updated 2 months ago
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆385Updated 10 months ago
- llama-omni训练代码复现☆59Updated 2 months ago
- The repo provides information about KeSpeech dataset.☆137Updated 2 years ago
- GPT-SoVITS2☆214Updated 8 months ago
- ✨✨Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM☆298Updated 3 months ago
- KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-…☆504Updated last year
- ☆17Updated 5 months ago