gpt-omni/mini-omni issues and pull requests

#100 - Empty Audio for Gradio

Issue - State: open - Opened by MarcoFerreiraPerson about 1 month ago

#99 - 输入只能为单一模态吗，仅语音/文本，不能是语音+文本吗

Issue - State: open - Opened by chaunceyliu30 about 1 month ago - 1 comment

#98 - docker

Issue - State: open - Opened by jacky080808 about 2 months ago

#97 - CUDA error: device-side assert triggered

Issue - State: open - Opened by Btlmd about 2 months ago - 1 comment

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

Issue - State: open - Opened by yufeng97 about 2 months ago

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

Issue - State: open - Opened by chaunceyliu30 about 2 months ago - 1 comment

#94 - tts-adapter的作用

Issue - State: open - Opened by william-ljz about 2 months ago - 1 comment

#93 - 关于layershift的作用

Issue - State: open - Opened by anliyuan about 2 months ago - 1 comment

#92 - How can I use my microphone in WSL?

Issue - State: open - Opened by duj12 about 2 months ago - 1 comment

#91 - Make download stats work

Pull Request - State: open - Opened by NielsRogge about 2 months ago

#90 - API_URL=http://0.0.0.0:60808/chat python3 webui/omni_gradio.py

Issue - State: open - Opened by tianke0711 about 2 months ago - 2 comments

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

Issue - State: open - Opened by tianke0711 about 2 months ago - 2 comments

#88 - ModuleNotFoundError: No module named 'pyaudio'

Issue - State: open - Opened by jxyk2007 about 2 months ago

#87 - 无法下载huggingface.co下载模型的，这个办法

Issue - State: open - Opened by jxyk2007 about 2 months ago - 1 comment

#86 - 能不能对接自己的大模型？

Issue - State: open - Opened by jxyk2007 about 2 months ago - 1 comment

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

Issue - State: open - Opened by CrazyWan528 about 2 months ago

#84 - Max retries exceeded with url: /hubertsiuzdak/snac_24khz/resolve/main/config.json

Issue - State: open - Opened by sankexin about 2 months ago - 2 comments

#83 - 生成的回答无法在gradio内播放

Issue - State: closed - Opened by Liu-Xiaoyan97 about 2 months ago - 2 comments

#82 - 使用远程服务器运行gradio，内网穿透后报错

Issue - State: closed - Opened by Liu-Xiaoyan97 about 2 months ago - 1 comment

#81 - 关于loss函数

Issue - State: closed - Opened by anliyuan about 2 months ago - 2 comments

#80 - Delay pattern decodding

Issue - State: open - Opened by wangers about 2 months ago - 2 comments

#79 - NotImplementedError: Cannot copy out of meta tensor; no data!

Issue - State: open - Opened by lucasjinreal about 2 months ago - 1 comment

#78 - require for training code

Issue - State: closed - Opened by CrazyBoyM about 2 months ago - 6 comments

#77 - Are there any plans to open up other TTS?

Issue - State: closed - Opened by MathewWuZJ about 2 months ago - 3 comments

#76 - Getting error when trying run gradio demo

Issue - State: closed - Opened by hp2413 2 months ago - 2 comments

#75 - How to solve the problem of not being able to access huggingface?

Issue - State: open - Opened by Donnie88 2 months ago - 2 comments

#74 - Chinese asr task support

Issue - State: closed - Opened by hosea7456 2 months ago - 2 comments

#73 - PydanticSchemaGenerationError using gradio

Issue - State: closed - Opened by boji123 2 months ago - 1 comment

#72 - What are the advantages of audio-to-audio compared to text-to-audio?

Issue - State: open - Opened by beetlebum233 2 months ago - 5 comments

#71 - 原部署代码中一个不够robust比较容易导致error的小问题

Issue - State: open - Opened by spectaclecs 2 months ago - 1 comment

#70 - gradio web report error after recording #69

Issue - State: closed - Opened by Emotibot5 2 months ago - 5 comments

#69 - gradio web report error after recording

Issue - State: closed - Opened by Emotibot5 2 months ago

#68 - streamlit error when click "start" button.

Issue - State: closed - Opened by Emotibot5 2 months ago - 4 comments

#67 - Architecture difference from technical report?

Issue - State: closed - Opened by sphmel 2 months ago - 9 comments

#66 - fix typo

Pull Request - State: closed - Opened by Lollipop 2 months ago - 1 comment

#65 - 推理报错：CUDA error: an illegal memory access was encountered

Issue - State: closed - Opened by yz53665 2 months ago - 2 comments

#64 - Segmentation fault (core dumped)

Issue - State: closed - Opened by hexastrayer 2 months ago

#63 - Can we change base model? for LLM and TTS in batch processing?

Issue - State: closed - Opened by ankit-chotaliya 2 months ago - 5 comments

#62 - 运行server.py，进度条只加载到4%，这正常吗

Issue - State: closed - Opened by YMMF007 2 months ago - 4 comments

#61 - 这个模型后续还会继续做迭代维护吗

Issue - State: closed - Opened by liangwq 2 months ago - 15 comments

#60 - The audio is shorter than the generated text and doesn't say the whole thing.

Issue - State: closed - Opened by Enchante503 2 months ago - 2 comments

#59 - Is there any possibility for RAG with Mini-Omni?

Issue - State: closed - Opened by yash-chudasama 2 months ago - 4 comments

#58 - Windows 11 ModuleNotFoundError: No module named 'lightning'

Issue - State: closed - Opened by Kingbadger3d 2 months ago - 4 comments

#57 - 文本转语音是不是无法支持中文？输入中文文本能否输出中文语音？

Issue - State: closed - Opened by AngGaGim 2 months ago - 3 comments

#56 - 运行 streamlit一直处于listen状态

Issue - State: closed - Opened by VJJJJJJ1 2 months ago - 4 comments

#55 - Problem with version torch 2.3.1

Issue - State: closed - Opened by MatienkoAndrew 2 months ago - 1 comment

#54 - 主界面录音结束后,出现错误,我的声音可以播放

Issue - State: closed - Opened by taozhiyuai 2 months ago - 2 comments

#53 - 如果我的业务场景是这样的。。。

Issue - State: closed - Opened by k2o333 2 months ago - 5 comments

#52 - run webui/omni_streamlit.py failed with import name 'get_speech_timestamps' from 'utils'

Issue - State: closed - Opened by alexhegit 2 months ago - 3 comments

#51 - 运行omni_streamlit.py的错误

Issue - State: closed - Opened by taozhiyuai 2 months ago - 5 comments

#51 - 运行omni_streamlit.py的错误

Issue - State: closed - Opened by taozhiyuai 2 months ago - 5 comments

#50 - python3 server.py --ip '0.0.0.0' --port 60808的运行错误

Issue - State: closed - Opened by taozhiyuai 2 months ago - 5 comments

#49 - after recording voice from micro-phone, error

Issue - State: closed - Opened by taozhiyuai 2 months ago - 5 comments

#48 - docs: update README.md

Pull Request - State: closed - Opened by eltociear 2 months ago

#47 - gradio启动后局域网内无法访问该服务器7860端口

Issue - State: closed - Opened by keno-log 2 months ago - 3 comments

#46 - omni_gradio.py 执行错误

Issue - State: closed - Opened by taozhiyuai 2 months ago - 2 comments

#45 - 安装出错 pip install PyAudio==0.2.14

Issue - State: closed - Opened by taozhiyuai 2 months ago - 1 comment

#44 - mac support

Pull Request - State: open - Opened by kunci115 2 months ago - 6 comments

#43 - gradio Demo 报错

Issue - State: closed - Opened by xtdx 2 months ago - 2 comments

#42 - whisper.load_audio requires ffmpeg to work on your computer

Issue - State: closed - Opened by DanWork123 2 months ago - 1 comment

#41 - 用MAC电脑，即使用上MPS GPU了，运行webui/omni_streamlit.py，那是一个卡啊

Issue - State: closed - Opened by Aaron-genai-superdev 2 months ago - 2 comments

#40 - Start server but got 404 error

Issue - State: closed - Opened by irrikrlla 2 months ago - 2 comments

#39 - About text instructed audio generation

Issue - State: closed - Opened by MonolithFoundation 2 months ago - 2 comments

#38 - 如果我直接想让他把我读出的中文语音直接翻译成英文读出来应该调整那个参数或者方法就是同声传译应该怎么设置一下？

Issue - State: closed - Opened by anstonjie 2 months ago - 3 comments

#37 - Chat Mini-Omni Demo start 后提示没有输出设备

Issue - State: closed - Opened by future911 2 months ago - 10 comments

#36 - history

Issue - State: closed - Opened by kunci115 2 months ago - 1 comment

#35 - win10 部署后提示这个错误 AssertionError: Torch not compiled with CUDA enabled

Issue - State: closed - Opened by xie236393 2 months ago - 5 comments

#34 - error: python: src/hostapi/alsa/pa_linux_alsa.c:3641: PaAlsaStreamComponent_BeginPolling: Assertion `ret == self->nfds' failed.

Issue - State: closed - Opened by thor9king 2 months ago - 2 comments

#33 - feat:增加device 参数

Pull Request - State: closed - Opened by wuhongsheng 2 months ago - 1 comment

#32 - 再window11 下的 pycharm下配置好环境运行 python webui/omni_gradio.py 出现如下的错误

Issue - State: closed - Opened by anstonjie 2 months ago - 4 comments

#31 - windows11 下面启动python server.py --ip '0.0.0.0' --port 60808 出现下面的错误或者说 ./checkpoint/lit_model.pth 去哪里下载

Issue - State: closed - Opened by anstonjie 2 months ago - 4 comments

#30 - 运行server.py启动后，网页打开失败

Issue - State: closed - Opened by YMMF007 2 months ago - 2 comments

#29 - Update README.md

Pull Request - State: closed - Opened by Alumniminium 2 months ago - 1 comment

#28 - It seems doesn't work on Windows...

Issue - State: closed - Opened by SmerchProsto 2 months ago - 11 comments

#27 - Fix undefined variable 'tik' for non-API mode

Pull Request - State: closed - Opened by tengattack 2 months ago - 1 comment

#26 - 是否支持多轮对话？

Issue - State: closed - Opened by HQYSS 2 months ago - 1 comment

#25 - 无法使用 streamlit 启动

Issue - State: closed - Opened by future911 2 months ago - 33 comments

#24 - 无法识别系统的麦克风

Issue - State: closed - Opened by future911 2 months ago - 5 comments

#23 - Could I run on CPU on Mac pro?

Issue - State: closed - Opened by Aaron-genai-superdev 2 months ago - 9 comments

#22 - How to retrieve text midway before it gets synthesized?

Issue - State: closed - Opened by SoberSalman 2 months ago - 2 comments

#21 - how to use `curl` cli to get response

Issue - State: closed - Opened by BrenchCC 2 months ago - 4 comments

#20 - Change voice?

Issue - State: closed - Opened by Barnplaid 2 months ago - 1 comment

#19 - what is the fastest ? A1A2, asr, T1A2, T1T2, A1T2, A1A2-batch ?

Issue - State: closed - Opened by zoldaten 2 months ago - 1 comment

#18 - 4o

Pull Request - State: closed - Opened by Sudz 2 months ago - 1 comment

#17 - can u help me?

Issue - State: closed - Opened by tiandaoyuxi 2 months ago - 8 comments

#16 - 模型推理问题

Issue - State: closed - Opened by william-ljz 2 months ago - 6 comments

#15 - Fix typo in README.md

Pull Request - State: closed - Opened by shahrukhx01 2 months ago - 1 comment

#14 - 输出不支持中文么？

Issue - State: closed - Opened by kaixindelele 2 months ago - 15 comments

#13 - ConnectionError

Issue - State: closed - Opened by BahamutRU 2 months ago - 2 comments

#12 - Broken demos?

Issue - State: closed - Opened by nigelp 2 months ago - 5 comments

#11 - Training Code

Issue - State: closed - Opened by pashanitw 2 months ago - 12 comments

#10 - Generate text token and audio token at the same time is time costing, why not consider generate audio token only when it comes to speech2speech task?

Issue - State: closed - Opened by lucasjinreal 2 months ago - 10 comments

#9 - Hello , does dataset open?

Issue - State: closed - Opened by MonolithFoundation 2 months ago - 12 comments

GitHub / gpt-omni/mini-omni issues and pull requests