zmeet-ai / asr_demo
语音识别API,分实时语音和长语音离线上传识别,支持中英文等多达100个国家的语言实时转写和同声传译
☆64Updated 2 weeks ago
Alternatives and similar repositories for asr_demo:
Users that are interested in asr_demo are comparing it to the libraries listed below
- 重生之我是 AI 打工人。前世,我的身份默默无闻,来去匆匆,不知道自己将在何地出生。然而,命运给予了我难得的机会,让我重生为一名 AI 打工人。☆45Updated last year
- 支持各种感情的男女声音,支持实时和离线文本合成tts语音;支持单模特声音变声,语音速率调整,语音音量大小调整;支持自定义语音模型。☆58Updated 9 months ago
- VITS2 for Chinese speech | 最新VITS2中文语音合成☆130Updated last year
- 基于中文文本情绪分析自动切换参考音 频的 GPT-SoVITS 推理 Demo☆86Updated 10 months ago
- Sample Repository for the AlibabaCloud Bailian Speech SDK☆49Updated 3 weeks ago
- Pseudo Streaming SenseVoice with Hotwords☆162Updated 3 weeks ago
- 张艺谋(国师)一键声音克隆和恶搞文本生成项目☆17Updated last year
- 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☆66Updated last month
- Bert-vits2-V2.3 训练和推理☆45Updated 10 months ago
- ChatBilibili .基于Fastapi 和ChatGPT Embedding ,实时生成视频概要,检索上下文视频提问/聊天☆28Updated last year
- 沪语(上海话)ASR(语音识别)模型☆18Updated 8 months ago
- 基于 faster-whisper 的伪实时语音转写服务☆193Updated 4 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☆253Updated last year
- SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime☆78Updated 3 months ago
- “alibabacloud-nls-python-sdk提供使用阿里云智能语音服务的能力,包括语音识别、语音合成、文件转写等。”☆40Updated last month
- Bert-vits2转写和标注独立整合Webui,整合阿里FunAsr,必剪Asr以及Whisper大模型☆160Updated 6 months ago
- 【脱离复杂的环境配置和整合包,极简配置推理服务】从GPT-SoVITS项目里面提取出来的,纯粹的推理服务方案。☆228Updated 9 months ago
- 超快的中文普通话TTS☆117Updated 3 years ago
- 一个用于CosyVoice的api接口项目☆145Updated 3 weeks ago
- 语音数据集制作标记工具☆134Updated 2 years ago
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆55Updated 2 weeks ago
- ☆117Updated 7 months ago
- 将Wav2Lip和GFPGAN进行结合实现高清数字人说话视频☆29Updated last year
- 将音频或视频中的中文语音识别并导出为srt字幕,基于魔塔社区Paraformer模型☆101Updated 6 months ago
- ChatTTS HTTP API☆50Updated 7 months ago
- Documentation for Bert-VITS2☆22Updated last year
- 获取bilibili直播弹幕,使用WebSocket协议☆36Updated 6 months ago
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆223Updated last month
- 数字人开源项目 (Digital human project)☆144Updated 2 years ago