chenyangMl / keyword-spotLinks
端到端语音唤醒工具箱,从模型训练到模型推理。
☆117Updated 9 months ago
Alternatives and similar repositories for keyword-spot
Users that are interested in keyword-spot are comparing it to the libraries listed below
Sorting:
- ☆122Updated 2 years ago
- A enterprise-grade Voice Activity Detector from modelscope and funasr.☆102Updated 2 years ago
- 基于FunASR实现语音识别,包含常规版和ONNX版(推荐)。☆39Updated 8 months ago
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆569Updated 3 months ago
- Python Wrapper of Silero VAD☆54Updated last month
- Utilizes ONNX Runtime for audio denoising.☆54Updated this week
- Kaldi-compatible online fbank extractor without external dependencies☆107Updated this week
- A enterprise-grade Chinese-English code switch punctuator from funasr.☆24Updated last year
- 语音识别模型pytorch转ONNX转MNN,C++实现部署☆68Updated 2 years ago
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆389Updated last year
- 本项目使用了EcapaTdnn、ResNetSE、ERes2Net、CAM++等多种先进的声纹识别模型,同时本项目也支持了MelSpectrogram、Spectrogram、MFCC、Fbank等多种数据预处理方法☆267Updated last week
- Pseudo Streaming SenseVoice with Hotwords☆295Updated 3 months ago
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆71Updated 2 months ago
- PaddleSpeech TTS cpp☆39Updated 2 years ago
- ☆56Updated 11 months ago
- SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime☆95Updated 8 months ago
- paraformer(chinense asr) online onnx runtime for python☆45Updated last year
- TTS appalication based on modelscope KAN-TTS☆43Updated last year
- Utilizes ONNX Runtime for speech activity detection.☆25Updated this week
- ☆200Updated 8 months ago
- 修复funasr中seaco-paraformer导出onnx后没有时间戳的bug☆20Updated 9 months ago
- ASR教程: https://dataxujing.github.io/ASR-paper/☆25Updated 11 months ago
- 使用vllm加速cosyvoice2的推理☆340Updated last month
- The repo provides information about KeSpeech dataset.☆145Updated 2 years ago
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English.☆101Updated 3 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☆264Updated last year
- OpenSpeaker is a completely independent and open source speaker recognition project. It provides the entire process of speaker recognitio…☆64Updated 3 years ago
- 中文标点符号模型,可以给文本添加标点符号。☆142Updated 5 months ago
- 这是一个用C++实现ASR推理的项目,它依赖很少,安装也很简单,推理速度很快,在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来,数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小…☆524Updated 2 years ago
- MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction mode…☆213Updated 5 months ago