k2-fsa / sherpaLinks
Speech-to-text server framework with next-gen Kaldi
☆855Updated 2 weeks ago
Alternatives and similar repositories for sherpa
Users that are interested in sherpa are comparing it to the libraries listed below
Sorting:
- ☆1,320Updated last month
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆673Updated 3 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…☆543Updated 2 years ago
- Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, …☆1,594Updated 2 months ago
- Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit☆1,141Updated this week
- SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.☆533Updated 9 months ago
- FSA/FST algorithms, differentiable, with PyTorch compatibility.☆1,298Updated last month
- Port of Funasr's Sense-voice model in C/C++☆507Updated 2 weeks ago
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆411Updated last month
- Pseudo Streaming SenseVoice with Hotwords☆414Updated 9 months ago
- A 10000+ hours dataset for Chinese speech recognition☆582Updated 2 years ago
- [ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching☆1,213Updated 3 weeks ago
- Text Normalization & Inverse Text Normalization☆710Updated last month
- Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching☆750Updated last month
- 📣 商用级 开源语音自动识别程序库，开箱即用，全平台支持，中英文混合识别。A Cross-platform implementation of ASR inference. It's based on ONNXRuntime and FunASR. We provide …☆593Updated last year
- KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-…☆526Updated 2 years ago
- ☆145Updated 2 years ago
- The dataset of Speech Recognition☆444Updated last year
- Kaldi-compatible online fbank extractor without external dependencies☆137Updated 2 months ago
- VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design☆627Updated 2 years ago
- 端到端语音唤醒工具箱，从模型训练到模型推理。☆148Updated 4 months ago
- Tools for handling multimodal data in machine learning projects.☆1,099Updated 3 weeks ago
- 使用vllm加速cosyvoice2的推理☆465Updated 8 months ago
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆1,172Updated 2 weeks ago
- An Open Source Tools for Speaker Recognition☆633Updated last year
- 一个执着于让CPU\端侧-Model逼近GPU-Model性能的项目，CPU上的实时率(RTF)小于0.1☆474Updated 9 months ago
- SummerTTS 是一个基于C++的独立编译的中文和英文语音合成项目，可以本地运行不需要网络，而且没有额外的依赖，一键编译完成即可用于中文和英文的语音合成。SummerTTS is a standalone Chinese and English speech synt…☆520Updated 5 months ago
- Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.☆689Updated last month
- The official implementation of GTCRN, an ultra-lightweight SE model.☆521Updated 7 months ago
- Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.☆583Updated last week