cronrpc / Audio-Speaker-Needle-In-Haystack
Finding the most similar tone/color in a large collection of audio. 在一大堆音频中寻找最相似的音色。
☆13Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for Audio-Speaker-Needle-In-Haystack
- SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime☆74Updated last month
- Extension of ChatTTS, 3x Faster on Windows, Support Voice Cloning and Mobile Deployment☆25Updated 2 weeks ago
- Bert-VITS2 onnx推理版本☆40Updated 6 months ago
- paraformer(chinense asr) online onnx runtime for python☆36Updated 7 months ago
- ☆65Updated 11 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
- 基于达摩院视频切割技术的视频转换为短音频的vits数据集生成工具 A VITS Dataset Generation Tool for Converting Video to Short Audio Based on Damo Academy Video Cutting T…☆52Updated 10 months ago
- flow mirror models from JZX AI Labs☆40Updated last month
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆52Updated this week
- paraformer web server build with sanic☆19Updated last year
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English☆74Updated this week
- Bert-VITS2_V202本地一键推理☆19Updated 11 months ago
- ultimate vocal remover application run on linux ubuntu1604☆51Updated last year
- ☆19Updated 5 months ago
- Pseudo Streaming SenseVoice with Hotwords☆85Updated 2 weeks ago
- SpeechDenoiser: Real-Time Speech Denoising with ONNX Welcome to SpeechDenoiser, a simple and effective solution for real-time speech den…☆44Updated 3 months ago
- 用于SenseVoice的api项目，输出带时间戳字幕☆13Updated 3 weeks ago
- A enterprise-grade Voice Activity Detector from modelscope and funasr.☆65Updated last year
- Just a suturing monster project.☆37Updated last year
- Huawei Grad-TTS for Chinese☆45Updated last year
- Full version of wav2lip-onnx including face alignment and face enhancement and more...☆70Updated last month
- ☆13Updated 8 months ago
- Bert-VITS2项目bug多且教程不友好。本proj尽可能修复了Bert-vits2项目的bug，并且可一键启动训练。仅需50条目标说话人语音，获得稳定、快速的TTS模型。☆30Updated last month
- 实现基于4k视频的高分辨率人物换衣、虚拟试穿、物品替换☆51Updated 2 years ago
- 将任意人的音色转换为成千上万种不同音色☆25Updated last year
- A Tiny Project For ASR model training and Deployment☆27Updated 2 years ago
- VC Without Retrain!☆103Updated 6 months ago
- 基于 g2pW 提升 pypinyin 的准确性☆78Updated last year