gpt-omni/mini-omni

Issues

• Max retries exceeded with url: /hubertsiuzdak/snac_24khz/resolve/main/config.json

  #84 opened 3 months ago by sankexin
  4

• 训练时audio feature和text token pad到的长度

  #109 opened 2 months ago by vra
  2

• 【Training复现问题】index_copy_和计算梯度错误

  #111 opened 2 months ago by vra
  1

• 这个模型是声音用whisper转成 声音token，用token和LLM chat得到回答的 文字token， 最后将这个回答的文字token 用SNAC转换成声音？

  #116 opened 2 months ago by ssdutliuhaibo
  0

• Does folder utils need a __init__.py?

  #115 opened 2 months ago by login256
  0

• Audio Generation is Slow

  #103 opened 2 months ago by MarcoFerreiraPerson
  2

• 请问这个模型是回答问题是直接输出语音再转成文字，还是由大模型回答文字再同时转成声音？ 如果是前者，是这个模型跑起来就固定某个声音吗？

  #114 opened 2 months ago by ssdutliuhaibo
  0

• 关于模态融合是否引起效果下降的疑问

  #113 opened 2 months ago by xiaodongyichuan
  1

• 【Training复现问题】三个stage具体训练周期数

  #112 opened 2 months ago by vra
  0

• What are the advantages of audio-to-audio compared to text-to-audio?

  #72 opened 2 months ago by beetlebum233
  6

• VoiceAssistant-400K 数据集如何生成的

  #104 opened 2 months ago by ltcxjtu
  5

• Clarification on Joint vs. Separate Training of ASR and TTS Adapters

  #110 opened 2 months ago by aidenyzhang
  0

• require for training code

  #78 opened 3 months ago by CrazyBoyM
  11

• 不支持移动端访问主机部署streamlit的服务嘛？

  #106 opened 2 months ago by loredunk
  1

• VoiceAssistant-400K

  #107 opened 2 months ago by UestcJay
  3

• batch parallel decoding

  #108 opened 2 months ago by handsomelys
  2

• Question regarding data format and loss calculation in stage 1

  #101 opened 2 months ago by sphmel
  7

• OSError: [Errno -9996] Invalid input device (no default output device)

  #89 opened 2 months ago by tianke0711
  4

• 请问，您会开源训练或微调的方法吗？

  #102 opened 2 months ago by SevenMpp
  1

• 输入只能为单一模态吗，仅语音/文本，不能是语音+文本吗

  #99 opened 3 months ago by chaunceyliu30
  2

• docker

  #98 opened 3 months ago by jacky080808
  1

• pydantic.errors.PydanticSchemaGenerationError: Unable to generate pydantic-core schema for <class 'starlette.requests.Request'>

  #96 opened 3 months ago by yufeng97
  1

• How to train this model with my own audio-to-audio data, any insturctions or documentations?

  #95 opened 3 months ago by chaunceyliu30
  2

• tts-adapter的作用

  #94 opened 2 months ago by william-ljz
  2

• 关于layershift的作用

  #93 opened 2 months ago by anliyuan
  2

• API_URL=http://0.0.0.0:60808/chat python3 webui/omni_gradio.py

  #90 opened 2 months ago by tianke0711
  3

• 能不能对接自己的大模型？

  #86 opened 2 months ago by jxyk2007
  2

• The ubuntu system reports an error about ALSA, and I cannot get a voice reply.

  #85 opened 3 months ago by CrazyWan528
  1

• NotImplementedError: Cannot copy out of meta tensor; no data!

  #79 opened 2 months ago by lucasjinreal
  2

• Mini-Omni2 is out

  #105 opened 2 months ago by superFilicos
  0

• CUDA error: device-side assert triggered

  #97 opened 2 months ago by Btlmd
  1

• Empty Audio for Gradio

  #100 opened 2 months ago by MarcoFerreiraPerson
  2

• How can I use my microphone in WSL?

  #92 opened 3 months ago by duj12
  1

• Are there any plans to open up other TTS?

  #77 opened 3 months ago by MathewWuZJ
  3

• gradio web report error after recording #69

  #70 opened 3 months ago by Emotibot5
  5

• 推理报错：CUDA error: an illegal memory access was encountered

  #65 opened 3 months ago by yz53665
  2

• streamlit error when click "start" button.

  #68 opened 3 months ago by Emotibot5
  4

• 无法下载huggingface.co下载模型的，这个办法

  #87 opened 3 months ago by jxyk2007
  1

• 关于loss函数

  #81 opened 3 months ago by anliyuan
  2

• 生成的回答无法在gradio内播放

  #83 opened 3 months ago by Liu-Xiaoyan97
  2

• ModuleNotFoundError: No module named 'pyaudio'

  #88 opened 3 months ago by jxyk2007
  0

• Delay pattern decodding

  #80 opened 3 months ago by wangers
  2

• Chinese asr task support

  #74 opened 3 months ago by hosea7456
  2

• 使用远程服务器运行gradio，内网穿透后报错

  #82 opened 3 months ago by Liu-Xiaoyan97
  1

• Architecture difference from technical report?

  #67 opened 3 months ago by sphmel
  9

• Getting error when trying run gradio demo

  #76 opened 3 months ago by hp2413
  2

• How to solve the problem of not being able to access huggingface?

  #75 opened 3 months ago by Donnie88
  2

• PydanticSchemaGenerationError using gradio

  #73 opened 3 months ago by boji123
  1

• 原部署代码中一个不够robust比较容易导致error的小问题

  #71 opened 3 months ago by spectaclecs
  1

• gradio web report error after recording

  #69 opened 3 months ago by Emotibot5
  0