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
☆189Updated this week
Related projects ⓘ
Alternatives and complementary repositories for Whisper-Finetune
- ☆545Updated 5 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-…☆494Updated 10 months ago
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆888Updated 4 months ago
- ☆287Updated 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☆249Updated last year
- ☆173Updated last month
- Pseudo Streaming SenseVoice with Hotwords☆85Updated 2 weeks ago
- 基于 faster-whisper 的伪实时语音转写服务☆182Updated 2 months ago
- Port of Funasr's Sense-voice model in C/C++☆163Updated 3 weeks ago
- 📣 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 …☆508Updated 6 months ago
- 中文标点符号模型，可以给文本添加标点符号。☆130Updated 8 months ago
- API and websocket server for sensevoice. It has inherited some enhanced features, such as VAD detection, real-time streaming recognition,…☆222Updated 3 weeks ago
- TTS appalication based on modelscope KAN-TTS☆43Updated 7 months ago
- Text Normalization & Inverse Text Normalization☆480Updated last week
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆371Updated 5 months ago
- SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.☆445Updated 2 months 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☆254Updated 4 months ago
- A 10000+ hours dataset for Chinese speech recognition☆506Updated last year
- 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…☆487Updated last year
- 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。☆537Updated last year
- 端到端语音唤醒工具箱，从模型训练到模型推理。☆77Updated 2 months ago
- ☆82Updated 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☆229Updated last week
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆463Updated 3 months ago
- a gradio webui for faster whisper☆232Updated last year
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆52Updated this week
- The dataset of Speech Recognition☆387Updated 4 months ago
- 百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，时延低至800ms，低配置也可运行，支持打断☆40Updated this week
- The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.☆1,230Updated 3 months ago