shuaijiang / Whisper-Finetune
Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment
☆254Updated last week
Alternatives and similar repositories for Whisper-Finetune:
Users that are interested in Whisper-Finetune are comparing it to the libraries listed below
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆997Updated 2 months ago
- ☆665Updated 9 months ago
- Pseudo Streaming SenseVoice with Hotwords☆233Updated 3 weeks 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
- API and websocket server for sensevoice. It has inherited some enhanced features, such as VAD detection, real-time streaming recognition,…☆393Updated 5 months ago
- Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR be…☆832Updated last week
- ☆193Updated 6 months ago
- 使用vllm加速cosyvoice2的推理☆127Updated last 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
- 基于 faster-whisper 的伪实时语音转写服务☆204Updated 6 months ago
- Port of Funasr's Sense-voice model in C/C++☆313Updated last week
- 📣 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 …☆541Updated 10 months ago
- ☆348Updated 8 months ago
- 中文标点符号模型,可以给文本添加标点符号。☆140Updated 3 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
- Text Normalization & Inverse Text Normalization☆561Updated 4 months ago
- An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System☆406Updated this week
- A 10000+ hours dataset for Chinese speech recognition☆523Updated last year
- chinese speech pretrained models☆1,094Updated 7 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…☆506Updated 2 years ago
- 实时STT,连接OpenAI接口/智谱AI(流式LLM)和GPT-SOVITS/Edge-TTS,通过网页的方式,进行跨网络的服务调用,实现实时对话的效果☆348Updated 3 months ago
- ☆111Updated last year
- Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.☆141Updated this week
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆385Updated 10 months ago
- TTS appalication based on modelscope KAN-TTS☆43Updated 11 months ago
- Sample Repository for the AlibabaCloud Bailian Speech SDK☆138Updated last week
- 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☆260Updated last month
- 第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验,同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。☆553Updated last year
- 基于FunASR实现语音识别,包含常规版和ONNX版(推荐)。☆36Updated 5 months ago
- SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.☆483Updated this week