SenseVoice
SenseVoice copied to clipboard
FunAudioLLM
Multilingual Voice Understanding Model
To check that the finetune process is ok , i use 30w sentences for training I found it is very slow to prepare train.json. 8 hours passed, the train.json of...
Notice: In order to resolve issues more efficiently, please raise issue following the template. （注意：为了更加高效率解决您遇到的问题，请按照模板提问，补充细节） ## ❓ Questions and Help 设置的batch_size为128，但是得到的batchsize为1，导致微调失败 ### Before asking: 1. search the issues. 2. search...
Notice: In order to resolve issues more efficiently, please raise issue following the template. （注意：为了更加高效率解决您遇到的问题，请按照模板提问，补充细节） ## ❓ Questions and Help 数据安装文档使用sensevoice2jsonl 生成的数据，微调时加载数据出现 data is empty! ### Before asking: 1. search...
python api.py 或是用fastapi启动时  
SenseVoiceSmall微调是否支撑增加事件/情绪/语言类型？ 经查阅源代码后发现funast/models/sensevoice/model.py中line 640-647中给出了情绪、语言的编码字典，但并没有事件相关的，想请问可以通过微调增加模型能检测的事件/情绪/语言吗？
Notice: In order to resolve issues more efficiently, please raise issue following the template. （注意：为了更加高效率解决您遇到的问题，请按照模板提问，补充细节） ## 🐛 Bug 可以正常识别mp3格式文件，但是不能识别wav文件，会卡住不动,直到你ctrl+c ### To Reproduce Steps to reproduce the behavior (**always include the...
## ❓ Questions and Help #### What is your question? 如何在torch 2.4.0环境下使用sensevoice 我正在做一个纯本地运行的语音对话的项目，使用SenseVoice+LLM+GPT-SoVITS来达到语音对语音交流的效果，其中部分模块必须要使用torch2.4.0，所以求大佬帮忙看下SenseVoice这个项目怎么样才能在torch2.4.0环境下正常运行 异常见下图：  ①运行在纯净的虚拟环境下，仅将torch升级为2.4.0，python版本3.11.2； ②torchaudio的版本与torch同步； ③尝试过修改`weights_only=True`，除了少了几行提示其他没有区别） #### Code ```python from funasr import AutoModel from funasr.utils.postprocess_utils import rich_transcription_postprocess import...
How is it with recognizing other languages? From the description it appears that the model was trained on 50 languages. How can you use languages other than the standard ones?...
## ❓ Questions below is the generated output from the model, is there any chance I can ignore these rtf_avg,time_speech,time_escape from the model, as I only want to see the...
