Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / FunAudioLLM/SenseVoice issues and pull requests
#184 - sensevoicesmall微调
Issue -
State: open - Opened by Rayzian 13 days ago
Labels: question
#183 - 运行demo2.py,报错:IndexError: index 2 is out of bounds for dimension 1 with size 2
Issue -
State: open - Opened by JosenJin about 1 month ago
- 3 comments
Labels: bug
#182 - 为什么SenseVoiceSmall采用非自回归模型,而Large采用自回归模型
Issue -
State: open - Opened by xiaonengmiao about 1 month ago
Labels: question
#181 - 使用 funasr 推理能写成fastapi部署吗?
Issue -
State: open - Opened by 812781385 about 1 month ago
Labels: question
#180 - 我成功启动了webUI,可是访问不到
Issue -
State: open - Opened by 812781385 about 1 month ago
- 1 comment
#179 - 训练方言数据时acc为0
Issue -
State: open - Opened by sunneam about 1 month ago
Labels: question
#178 - ”我是“ 识别成”不是“,这种问题,怎么补救
Issue -
State: open - Opened by brucegamma about 1 month ago
Labels: question
#177 - 截止2025/1/1请问支持多人2,3个人聊天室场景吗?能否自动map哪个人哪个声音?
Issue -
State: open - Opened by JJP1946009858 about 2 months ago
Labels: question
#176 - fix demo onnx textnorm
Pull Request -
State: closed - Opened by DeoLeung about 2 months ago
#175 - demo_onnx.py运行报错
Issue -
State: open - Opened by Sekri0 about 2 months ago
- 5 comments
Labels: bug
#174 - 可用CPU跑吗?自己是mac电脑
Issue -
State: open - Opened by nianxiongdi about 2 months ago
- 1 comment
Labels: bug
#173 - Timestamp error may caused by audio file.
Issue -
State: open - Opened by Huowuge 2 months ago
- 7 comments
Labels: bug
#172 - 英文识别的原始结果不正常,还是给出的ITN结果
Issue -
State: open - Opened by Ziyi6 2 months ago
- 1 comment
Labels: question
#171 - SenseVoice怎么支持流式开发
Issue -
State: open - Opened by brucegamma 2 months ago
Labels: question
#170 - 为什么sensevoice模型的输入是N x T x 560?
Issue -
State: open - Opened by dlkht 2 months ago
- 1 comment
Labels: question
#169 - language参数的作用是啥?指定语言吗?但是无论指定哪种语言,输入音频是yue同样也能输出粤语,这正常吗?
Issue -
State: open - Opened by Jimmy-L99 2 months ago
Labels: question
#168 - 模型提供的http接口/api/v1/asr,java使用hutool工具类调用会报内部错误,请问有什么解决方法吗?
Issue -
State: open - Opened by niedamin 2 months ago
Labels: question
#167 - When using commit 530b2e3 for timestamp-based inference, IndexError: list index out of range
Issue -
State: open - Opened by NBStarry 3 months ago
Labels: question
#166 - ModuleNotFoundError: No module named 'typing_extensions'
Issue -
State: open - Opened by daixun0913 3 months ago
- 1 comment
Labels: question
#166 - ModuleNotFoundError: No module named 'typing_extensions'
Issue -
State: open - Opened by daixun0913 3 months ago
- 1 comment
Labels: question
#165 - 是否考虑开源large模型?
Issue -
State: open - Opened by MonolithFoundation 3 months ago
#165 - 是否考虑开源large模型?
Issue -
State: open - Opened by MonolithFoundation 3 months ago
- 1 comment
#164 - 运行dome1提示了一些没有注册的错误信息,不知道是为什么?
Issue -
State: open - Opened by hnxueque 3 months ago
- 7 comments
Labels: question
#163 - Is the SenseVoice-Large model currently commercialized?
Issue -
State: open - Opened by JinYuanZhang999 3 months ago
Labels: question
#162 - 关于 Speaker Interpolation 如何实现
Issue -
State: open - Opened by LongMarch7 3 months ago
Labels: question
#161 - 期待能有热词的更新
Issue -
State: open - Opened by liduowen 3 months ago
Labels: question
#161 - 期待能有热词的更新
Issue -
State: open - Opened by liduowen 3 months ago
- 1 comment
Labels: question
#160 - ValueError: Key SenseVoiceEncoderSmall already exists in encoder_classes
Issue -
State: closed - Opened by JinYuanZhang999 4 months ago
Labels: question
#160 - ValueError: Key SenseVoiceEncoderSmall already exists in encoder_classes
Issue -
State: closed - Opened by JinYuanZhang999 4 months ago
Labels: question
#159 - api测试时出现错误
Issue -
State: open - Opened by leanco1 4 months ago
Labels: question
#158 - 按操作文档finetune报错: styles = torch.LongTensor([[self.textnorm_int_dict[int(style)]] for style in text[:, 3]]).to(speech.device) IndexError: index 3 is out of bounds for dimension 1 with size 1
Issue -
State: open - Opened by eatoncys 4 months ago
- 5 comments
Labels: bug
#157 - 如何导出字幕格式的文件,?
Issue -
State: open - Opened by webkonglong 4 months ago
- 1 comment
Labels: question
#157 - 如何导出字幕格式的文件,?
Issue -
State: open - Opened by webkonglong 4 months ago
- 2 comments
Labels: question
#156 - Multi-language support like Whisper?
Issue -
State: open - Opened by haubui17062019 4 months ago
Labels: question
#156 - Multi-language support like Whisper?
Issue -
State: open - Opened by haubui17062019 4 months ago
Labels: question
#155 - 为什么demo1和demo2的识别example里中文音频的效果不一样?
Issue -
State: open - Opened by Hou-MY 4 months ago
- 2 comments
Labels: question
#155 - 为什么demo1和demo2的识别example里中文音频的效果不一样?
Issue -
State: open - Opened by Hou-MY 4 months ago
- 2 comments
Labels: question
#154 - 转换wav文件报错:Segmentation fault
Issue -
State: open - Opened by superbread93a 4 months ago
Labels: bug
#153 - How can I translate an input English audio into Chinese?
Issue -
State: open - Opened by yangyazhou97 4 months ago
#152 - 在使用VAD时,采样率对推理结果影响很大
Issue -
State: open - Opened by bigeyefish 4 months ago
Labels: question
#152 - 在使用VAD时,采样率对推理结果影响很大
Issue -
State: open - Opened by bigeyefish 4 months ago
Labels: question
#151 - sensevoice2jsonl生成数据报错
Issue -
State: open - Opened by Airgods 4 months ago
Labels: question
#151 - sensevoice2jsonl生成数据报错
Issue -
State: open - Opened by Airgods 4 months ago
- 1 comment
Labels: question
#150 - 语音转文字报错
Issue -
State: open - Opened by hjj-lmx 4 months ago
- 1 comment
Labels: bug
#150 - 语音转文字报错
Issue -
State: open - Opened by hjj-lmx 4 months ago
- 1 comment
Labels: bug
#149 - I want to know the hyperparameter settings when training SenseVoice-s
Issue -
State: open - Opened by zte-tcb 4 months ago
- 1 comment
Labels: question
#149 - I want to know the hyperparameter settings when training SenseVoice-s
Issue -
State: open - Opened by zte-tcb 4 months ago
- 1 comment
Labels: question
#148 - 如何指定只识别单个语言?
Issue -
State: open - Opened by maxin9966 4 months ago
Labels: question
#147 - The demo.py can not work correctly
Issue -
State: open - Opened by chongkuiqi 4 months ago
- 1 comment
Labels: bug
#146 - finetune custom data bug
Issue -
State: closed - Opened by canglangzhishuiz 4 months ago
Labels: bug
#146 - finetune custom data bug
Issue -
State: closed - Opened by canglangzhishuiz 4 months ago
- 1 comment
Labels: bug
#145 - What does "non-autoregressive" mean specifically?
Issue -
State: open - Opened by chansonzhang 4 months ago
- 1 comment
Labels: question
#144 - 请问SenseVoice支持context吗?或者还有其他什么支持context的ASR模型吗?
Issue -
State: open - Opened by Airgods 4 months ago
Labels: question
#143 - No code-path supporting cache-aware streaming for SenseVoiceSmall Model?
Issue -
State: open - Opened by Jacob-Bishop 4 months ago
- 1 comment
Labels: question
#142 - onnx模型在输入多段音频时,有些asr的结果为空,有什么解决的办法吗
Issue -
State: closed - Opened by foolishcqx 4 months ago
- 3 comments
Labels: question
#141 - sensevoice-onnx模型每次识别新的(之前没有见过的)输入语音都要加载10几秒,很影响推理效率,这个问题如何解决?
Issue -
State: open - Opened by Nicksooooo 4 months ago
- 3 comments
Labels: bug
#140 - 可以实现有标点、数字不转化为阿拉伯数字吗?
Issue -
State: closed - Opened by TinaChen95 4 months ago
- 1 comment
Labels: question
#139 - SenseVoiceSmall微调如何实现语种增加
Issue -
State: open - Opened by Itsuka-Xx 4 months ago
- 1 comment
Labels: question
#138 - 可以返回情感识别结果的置信度吗?
Issue -
State: open - Opened by lgbest123 5 months ago
- 1 comment
Labels: question
#137 - 我创建了ComfyUI-FunAudioLLM插件,包含了SenseVoice和CosyVoice的功能
Issue -
State: open - Opened by SpenserCai 5 months ago
- 1 comment
#136 - 效果很好想使用,请问会涉及商业化侵权吗
Issue -
State: closed - Opened by yangpeng666 5 months ago
- 1 comment
Labels: question
#135 - 无法识别,返回是空
Issue -
State: closed - Opened by JosenJin 5 months ago
- 3 comments
Labels: bug
#134 - 根据文档做模型微调时执行脚本报错,batch_size = input.size(0) AttributeError: 'str' object has no attribute 'size'
Issue -
State: closed - Opened by EssinZhang 5 months ago
- 2 comments
Labels: question
#133 - 如何离线运行
Issue -
State: closed - Opened by includewins0ck2 5 months ago
- 1 comment
Labels: question
#132 - 导出的onnx 模型比 正常的模型推理慢
Issue -
State: closed - Opened by DuBaiSheng 5 months ago
- 2 comments
Labels: question
#131 - 面对一些任务时,翻译的不准,不知道除了sensevoice small,是否还有其他可以替换的预训练模型可以拿来用下?
Issue -
State: open - Opened by Airgods 5 months ago
Labels: question
#130 - 如何限定语言
Issue -
State: closed - Opened by MonolithFoundation 5 months ago
- 4 comments
#129 - auto如何在支持的语种里取部分语言?
Issue -
State: open - Opened by Zer0TheObserver 5 months ago
- 3 comments
Labels: question
#128 - sensevoice2jsonl is too slow for 2 millions enries. any way to speed it up? Looks like it is not using gpu during this phase.
Issue -
State: open - Opened by prsasatt 5 months ago
Labels: question
#127 - 每次cpu调用后内存都会增加
Issue -
State: closed - Opened by Eoous 5 months ago
- 4 comments
Labels: question
#126 - 开源版支持其他语种吗?除了那五种
Issue -
State: closed - Opened by herbiel 5 months ago
- 1 comment
#125 - 【请教】数据集的各个字段解释
Issue -
State: closed - Opened by LateLinux 5 months ago
- 1 comment
Labels: question
#124 - 运行模型需要什么配置。
Issue -
State: open - Opened by fzfz666 5 months ago
- 1 comment
Labels: question
#123 - Can we generate the transcript including audio events?
Issue -
State: open - Opened by SutirthaChakraborty 5 months ago
- 1 comment
Labels: question
#122 - 希望能加说话人识别功能
Issue -
State: open - Opened by yumianhuli1 5 months ago
- 1 comment
Labels: question
#121 - 请问如果要微调以支持检测特殊背景声音,一般需要准备多少标注数据?
Issue -
State: open - Opened by frazy 6 months ago
Labels: question
#120 - ONNX模型转换报错,模型无法使用
Issue -
State: open - Opened by salier 6 months ago
- 4 comments
Labels: bug
#119 - KeyError: 94
Issue -
State: closed - Opened by wangjiancheng-123 6 months ago
- 1 comment
Labels: bug
#118 - 什么时候支持流式识别呢
Issue -
State: open - Opened by summerHearts 6 months ago
- 7 comments
Labels: question
#117 - 是否能支持nodeJS调用,比如nodeJS版本的ONNX
Issue -
State: closed - Opened by zhouzhili 6 months ago
- 2 comments
Labels: question
#116 - 非常厉害的模型,CPU占用确实比Paraformer模型低很多。希望能增加分角色功能和热词功能。
Issue -
State: open - Opened by wjq8811 6 months ago
- 2 comments
Labels: question
#115 - 运行web.py 访问7860无法正常访问
Issue -
State: open - Opened by firekirin67 6 months ago
- 1 comment
Labels: question
#114 - url地址过长会报错 filename too long
Issue -
State: open - Opened by hjj-lmx 6 months ago
Labels: bug
#113 - 返回的文本有一些表情符号,这种怎么去掉
Issue -
State: open - Opened by hjj-lmx 6 months ago
- 9 comments
Labels: question
#112 - 是否支持情感分类,怎样使用代码进行情感分类?
Issue -
State: open - Opened by zzhdbw 6 months ago
- 1 comment
Labels: question
#111 - 支持多人对话的场景
Issue -
State: open - Opened by hehuang139 6 months ago
- 3 comments
Labels: question
#110 - 是否支持华为Ascend npu
Issue -
State: open - Opened by lq0104 6 months ago
- 1 comment
Labels: question
#109 - SenseVoice-Small 现在只支持语音识别功能吗,如果有其他功能,如何设置
Issue -
State: open - Opened by hhnshiyi 6 months ago
Labels: question
#108 - 微调时batch_size设置问题
Issue -
State: open - Opened by yangppde 6 months ago
Labels: question
#107 - why is it so slow to prepare train.json
Issue -
State: open - Opened by housebaby 6 months ago
Labels: question
#106 - ban_emo_unk doesn't work
Issue -
State: open - Opened by PMPBinZhang 6 months ago
- 2 comments
Labels: bug
#105 - "AssertionError: iic/SenseVoiceSmall is not registered" while deploying it on server via fastapi
Issue -
State: closed - Opened by abysee 6 months ago
- 2 comments
Labels: question
#104 - To create a public link, set `share=True` in `launch()`.
Issue -
State: closed - Opened by luckyleitwo 6 months ago
- 1 comment
Labels: question
#103 - 微调训练模型,训练loss收敛,验证loss不收敛
Issue -
State: open - Opened by wuhongsheng 6 months ago
- 2 comments
Labels: question
#102 - finetune model size 有2.8G 原版的模型只有1个G
Issue -
State: closed - Opened by wuhongsheng 6 months ago
- 1 comment
Labels: question
#101 - sensevoice 微调 加载数据出错
Issue -
State: open - Opened by yangppde 6 months ago
- 3 comments
Labels: question
#100 - 微调训练报 cuda 同步超时 2x4090
Issue -
State: closed - Opened by wuhongsheng 6 months ago
- 1 comment
Labels: question
#99 - 模型支持输出文本对应的时间戳吗
Issue -
State: open - Opened by kirayomato 6 months ago
- 10 comments
Labels: question
#98 - 运行api报错
Issue -
State: open - Opened by EINEZIO 6 months ago
Labels: bug
#97 - 能自定義 热词嗎
Issue -
State: open - Opened by TCWPanda 6 months ago
- 5 comments
Labels: question