首页下载资源人工智能Mini-Omni：语言模型可以在流式传输中聆听、交谈和思考

ZIPMini-Omni：语言模型可以在流式传输中聆听、交谈和思考

fenglingguitar4.38MB需要积分:1

资源文件列表:

mini-omni.zip 大约有80个文件
  1. mini-omni/
  2. mini-omni/tokenizer_config.json 1.26KB
  3. mini-omni/lit_model.pth 135B
  4. mini-omni/tokenizer.json 6.7MB
  5. mini-omni/README.md 1.09KB
  6. mini-omni/.gitattributes 1.48KB
  7. mini-omni/model_config.yaml 848B
  8. mini-omni/.git/
  9. mini-omni/frameworkv3.jpg 167.82KB
  10. mini-omni/.git/config 307B
  11. mini-omni/.git/objects/
  12. mini-omni/.git/HEAD 21B
  13. mini-omni/.git/info/
  14. mini-omni/.git/logs/
  15. mini-omni/.git/description 73B
  16. mini-omni/.git/hooks/
  17. mini-omni/.git/refs/
  18. mini-omni/.git/index 625B
  19. mini-omni/.git/packed-refs 112B
  20. mini-omni/.git/objects/95/
  21. mini-omni/.git/objects/68/
  22. mini-omni/.git/objects/3b/
  23. mini-omni/.git/objects/33/
  24. mini-omni/.git/objects/b3/
  25. mini-omni/.git/objects/da/
  26. mini-omni/.git/objects/f4/
  27. mini-omni/.git/objects/eb/
  28. mini-omni/.git/objects/pack/
  29. mini-omni/.git/objects/7b/
  30. mini-omni/.git/objects/2f/
  31. mini-omni/.git/objects/6e/
  32. mini-omni/.git/objects/info/
  33. mini-omni/.git/objects/98/
  34. mini-omni/.git/objects/a0/
  35. mini-omni/.git/objects/a7/
  36. mini-omni/.git/objects/a6/
  37. mini-omni/.git/objects/46/
  38. mini-omni/.git/info/exclude 240B
  39. mini-omni/.git/logs/HEAD 189B
  40. mini-omni/.git/logs/refs/
  41. mini-omni/.git/hooks/commit-msg.sample 896B
  42. mini-omni/.git/hooks/pre-rebase.sample 4.78KB
  43. mini-omni/.git/hooks/pre-commit.sample 1.6KB
  44. mini-omni/.git/hooks/applypatch-msg.sample 478B
  45. mini-omni/.git/hooks/fsmonitor-watchman.sample 4.62KB
  46. mini-omni/.git/hooks/pre-receive.sample 544B
  47. mini-omni/.git/hooks/prepare-commit-msg.sample 1.46KB
  48. mini-omni/.git/hooks/post-update.sample 189B
  49. mini-omni/.git/hooks/pre-merge-commit.sample 416B
  50. mini-omni/.git/hooks/pre-applypatch.sample 424B
  51. mini-omni/.git/hooks/pre-push.sample 1.34KB
  52. mini-omni/.git/hooks/update.sample 3.56KB
  53. mini-omni/.git/hooks/push-to-checkout.sample 2.72KB
  54. mini-omni/.git/refs/heads/
  55. mini-omni/.git/refs/tags/
  56. mini-omni/.git/refs/remotes/
  57. mini-omni/.git/objects/95/341e1d6ae4b5086e60f09e98f1a4ef42aca7fa 91B
  58. mini-omni/.git/objects/68/f1da89b775caff935efc24d5241bd10eeb677c 126B
  59. mini-omni/.git/objects/3b/7ba72c19d27aac21f7967459a282f92659d48b 273B
  60. mini-omni/.git/objects/33/ea6c72ebb92a237fa2bdf26c5ff16592efcdae 2.2MB
  61. mini-omni/.git/objects/b3/a695259f376d4eaf2e78d8d995ddf1fea57736 857B
  62. mini-omni/.git/objects/da/6c66ccafbb524fe0d3f046053124239d67c75c 475B
  63. mini-omni/.git/objects/f4/b55f917af273d0dc98b67ec249f6445dd385f5 489B
  64. mini-omni/.git/objects/eb/09342a1d90c60ff41325e0030971ff25e9fecd 652B
  65. mini-omni/.git/objects/7b/e5fc7f47d5db027d120b8024982df93db95b74 37B
  66. mini-omni/.git/objects/2f/9d8d44c202347e18efe7ed842959c1f5b3b6f6 137.38KB
  67. mini-omni/.git/objects/6e/a96fe583cf6200c1133368ad38011aac72eeeb 810B
  68. mini-omni/.git/objects/98/96323e09177b32edcceedd565a086a91d029ab 852B
  69. mini-omni/.git/objects/a0/dec2a89823c6136f481649b303d5905a31f866 234B
  70. mini-omni/.git/objects/a7/22089c58869095607cb52d19b2f5a0c82cfe15 850B
  71. mini-omni/.git/objects/a6/344aac8c09253b3b630fb776ae94478aa0275b 224B
  72. mini-omni/.git/objects/46/a665ebf65e1fb9b3ea646bfd6dc20618137d5c 234B
  73. mini-omni/.git/logs/refs/heads/
  74. mini-omni/.git/logs/refs/remotes/
  75. mini-omni/.git/refs/heads/main 41B
  76. mini-omni/.git/refs/remotes/origin/
  77. mini-omni/.git/logs/refs/heads/main 189B
  78. mini-omni/.git/logs/refs/remotes/origin/
  79. mini-omni/.git/refs/remotes/origin/HEAD 30B
  80. mini-omni/.git/logs/refs/remotes/origin/HEAD 189B

资源介绍:

Mini-Omni 是一个开源多模型大型语言模型，可以一边听、一边说，一边思考。具有实时端到端语音输入和流音频输出对话功能。 特征 实时语音对话功能。无需额外的 ASR 或 TTS 模型。 一边说话一边思考，能够同时生成文本和音频。 流音频输出功能。 通过“音频到文本”和“音频到音频”批量推理进一步提升性能。
--- license: mit language: - en base_model: Qwen/Qwen2-0.5B ---

Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

🤗 Hugging Face | 📖 Github | 📑 Technical report

Mini-Omni is an open-source multimodel large language model that can **hear, talk while thinking**. Featuring real-time end-to-end speech input and **streaming audio output** conversational capabilities.

## Features ✅ **Real-time speech-to-speech** conversational capabilities. No extra ASR or TTS models required. ✅ **Talking while thinking**, with the ability to generate text and audio at the same time. ✅ **Streaming audio outupt** capabilities. ✅ With "Audio-to-Text" and "Audio-to-Audio" **batch inference** to further boost the performance. **NOTE**: please refer to https://github.com/gpt-omni/mini-omni for more details.
100+评论
captcha

    相关资源

    1. dlib-19.17.0-cp37-cp37m-win-amd64.whl

      nddbblzx#后端ZIP2.95MB6月前
      资源摘要:dlib-19.17.0-cp37-cp37m-win_amd64.whl记得解压记得解压

    2. 撮合交易的购售双方申报信息及节点通道信息

      m0_71299620#数据库ZIP128.22KB6月前
      资源摘要:算例，节点间连接关系，撮合交易申报信息

    3. 算法-动态规划-斐波那契模型

      weixin_72066135#后端ZIP6.26MB6月前
      资源摘要:本资源是解决算法中动态规划中第一章斐波那契模型。我们通过四道例题来学习了什么是动态规划，从泰波那契数列开始，到解码方法结束。以四道典型例题，对我们的斐波那契数列模型有了新的认识，在解决个问题中，我将每道题的解题思路一画图版的形式展示出来，放在资源中，工大家学习参考，同时在堆第一章总结的思维导图也放在压缩包之中，供大家参考。

    4. 111

      2301_77038789#前端ZIP429.06KB6月前
      资源摘要:qqq

    5. 单片机基础仿真与创客拓展99.zip

      2401_84696124#行业研究ZIP14.5MB6月前
      资源摘要:单片机基础仿真与创客拓展99.zip

    6. 2021_9_2Qt-main.zip

      m0_74810392#行业研究ZIP3.22MB6月前
      资源摘要:2021_9_2Qt-main.zip

    7. Android阶段性学习成果

      qia451#移动开发ZIP32.65MB6月前
      资源摘要:基于Java的Android studio开发的一款简易的App。采用MVP架构有用户登录以及内容编辑和工具设置界面设计简易

    8. 人脸识别模型,解压后放置到工程public文件夹下

      weixin_50194471#前端ZIP10.33MB6月前
      资源摘要:人脸识别模型,解压后放置到工程public文件夹下
    站长QQ:九六九五七三七