Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / modelscope/FunASR issues and pull requests

#2093 - websocket service cannot do real-time recognition after deployment with docker

Issue - State: closed - Opened by ruifengma about 2 months ago - 2 comments
Labels: question

#2092 - RuntimeError: mixed dtype (CPU): expect parameter to have scalar type of Float

Issue - State: closed - Opened by icestoneking about 2 months ago - 1 comment
Labels: question

#2091 - docker cpu0.45时间戳bug

Issue - State: open - Opened by cuiyuanzhe about 2 months ago - 4 comments
Labels: bug

#2090 - 离线GPU版本镜像报错

Issue - State: open - Opened by ZTFsmart about 2 months ago - 2 comments
Labels: question

#2089 - 服务器用docker运行发生异常

Issue - State: open - Opened by randsoy about 2 months ago - 2 comments
Labels: bug

#2088 - Update readme_cn.md misspelling

Pull Request - State: closed - Opened by learningpro about 2 months ago

#2087 - The English model is not working properly

Issue - State: open - Opened by treya-lin about 2 months ago
Labels: bug

#2086 - 如果要训练一个中文标点检测模型，那么数据的准备格式是怎样的呢？

Issue - State: closed - Opened by wanganddi0918 about 2 months ago - 2 comments
Labels: question

#2085 - Passing wrong arguments into compute_mask_indices

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

#2084 - 请问如何使用FunASR进行语种的识别？

Issue - State: open - Opened by yumianhuli1 about 2 months ago - 1 comment
Labels: question

#2083 - sensevoice 增加置信度输出

Pull Request - State: open - Opened by wantt about 2 months ago - 1 comment

#2081 - ffmpeg处理pcm格式音频

Issue - State: closed - Opened by wwfcnu about 2 months ago - 1 comment
Labels: bug

#2080 - 如何用FunASR预先判断音频是中文还是英文？

Issue - State: closed - Opened by yumianhuli1 about 2 months ago - 1 comment
Labels: question

#2079 - 如何使用JAVA来实现实时语音翻译功能

Issue - State: open - Opened by Liuhangshuo about 2 months ago - 2 comments
Labels: question

#2078 - /examples/industrial_data_pretraining/paraformer/finetune.sh运行报错

Issue - State: open - Opened by wuyuzhe about 2 months ago - 4 comments
Labels: bug

#2077 - How to export a fine-tuned model to ONNX format and deploy it to run in a WebSocket or docker？

Issue - State: open - Opened by honghan2023 about 2 months ago - 1 comment
Labels: question

#2076 - 实时语音听写服务后续会考虑支持时间戳吗

Issue - State: closed - Opened by johnshawn-david about 2 months ago - 1 comment
Labels: question

#2075 - fix bug, 1 fix cuda oom, 2 fix choose a window size 400 that is [2, 0]

Pull Request - State: closed - Opened by nixonjin about 2 months ago

#2072 - 有多人说话场景分离的模型吗？

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

#2068 - sencevoice模型无法和punc模型与cam模型一起加载

Issue - State: open - Opened by plancktree 2 months ago - 2 comments
Labels: bug

#2067 - 可以区分说话人角色和数量

Issue - State: closed - Opened by ybshaw 2 months ago - 2 comments
Labels: question

#2066 - 下载funasr:funasr-runtime-sdk-gpu-0.1.1，下到一半提示这个是什么问题

Issue - State: closed - Opened by lisong888 2 months ago - 1 comment
Labels: question

#2065 - 热词和时间戳无法同时生效

Issue - State: closed - Opened by buaibieshanghai 2 months ago - 8 comments
Labels: question

#2064 - Paraformer-zh模型不加载VAD模型无法识别标点

Issue - State: closed - Opened by SinlinLi 2 months ago - 1 comment
Labels: bug

#2062 - 在一台服务器上，开多个服务，推理速度上不去

Issue - State: open - Opened by xiaoheiNLP 2 months ago - 4 comments
Labels: question

#2060 - ValueError: math domain error

Issue - State: closed - Opened by lsdlh 2 months ago - 1 comment
Labels: bug

#2058 - funasr-runtime-sdk-gpu-0.1.1版本运行过程中出现异常

Issue - State: open - Opened by liurongjie174 2 months ago - 3 comments
Labels: bug

#2057 - AssertionError: paraformer-zh-streaming is not registered

Issue - State: closed - Opened by wangaolin1 2 months ago - 1 comment
Labels: bug

#2056 - 不行，windows11 on arm64 电脑上运行不了

Issue - State: closed - Opened by wmx-github 2 months ago

#2054 - 离线文件服务websocket解析音频后，返回的结果不对

Issue - State: closed - Opened by wangguo1230 2 months ago - 1 comment
Labels: bug

#2053 - any support for fine-tune audio data longer than 1 minute?

Issue - State: open - Opened by Jack-Lin-gif 2 months ago - 1 comment
Labels: question

#2052 - speech_ngram_lm_zh-cn-ai-wesp-fst 这个模型怎么做增量训练

Issue - State: closed - Opened by liuwenchang 2 months ago - 1 comment
Labels: question

#2051 - 多段语音并行识别失败问题

Issue - State: closed - Opened by MENGHAH 2 months ago - 1 comment
Labels: question

#2050 - "emotion2vec_plus_large" model does not exist

Issue - State: closed - Opened by Rob-Nafous 2 months ago - 2 comments
Labels: bug

#2049 - 文档写的真多，过多了

Issue - State: closed - Opened by Noah0115 2 months ago
Labels: question

#2048 - 实时转写 Docker 服务如何使用讲话人识别？

Issue - State: open - Opened by purerosefallen 2 months ago - 3 comments
Labels: question

#2044 - docker部署，wave.Error: unknown format: 6，ffmpeg没有如期运行

Issue - State: open - Opened by Jack-Lin-gif 2 months ago - 1 comment
Labels: bug

#2042 - A10卡GPU推理效率和CPU持平，不清楚是什么地方的问题

Issue - State: open - Opened by lanyuer 2 months ago - 1 comment
Labels: question

#2041 - 微调seaco_paraformer模型单机多卡出现错误

Issue - State: closed - Opened by gzqqqqqq 3 months ago - 3 comments
Labels: bug

#2040 - ONNX Export of Pretrained models outputs garbage

Issue - State: open - Opened by andreystarenky 3 months ago - 2 comments
Labels: question

#2040 - ONNX Export of Pretrained models outputs garbage

Issue - State: open - Opened by andreystarenky 3 months ago - 2 comments
Labels: question

#2039 - 加入spk_model后，一个模型似乎只能推理一次

Issue - State: open - Opened by orangenuinee 3 months ago - 2 comments
Labels: question

#2038 - filename too long

Issue - State: open - Opened by hjj-lmx 3 months ago
Labels: bug

#2038 - filename too long

Issue - State: open - Opened by hjj-lmx 3 months ago
Labels: bug

#2037 - docker拉取镜像失败，只能拉取部分，导致服务端运行失败

Issue - State: closed - Opened by Xuyaoyan 3 months ago - 2 comments
Labels: bug

#2036 - pip insatll funasr 以后，logging 不能正常打印

Issue - State: open - Opened by dibaotian 3 months ago - 1 comment
Labels: bug

#2036 - pip insatll funasr 以后，logging 不能正常打印

Issue - State: open - Opened by dibaotian 3 months ago
Labels: bug

#2034 - update web

Pull Request - State: closed - Opened by bltcn 3 months ago

#2033 - docker部署funasr，镜像是funasr-runtime-sdk-cpu-0.4.5，如何识别不同人说话

Issue - State: closed - Opened by jaychuo 3 months ago - 1 comment
Labels: question

#2031 - 现在这个FunASR能用在普通的商业上吗？

Issue - State: open - Opened by dyjiangjh 3 months ago
Labels: question

#2031 - 现在这个FunASR能用在普通的商业上吗？

Issue - State: closed - Opened by dyjiangjh 3 months ago - 1 comment
Labels: question

#2030 - 麦克风说话的音频的保存问题

Issue - State: open - Opened by lxb0425 3 months ago
Labels: question

#2030 - 麦克风说话的音频的保存问题

Issue - State: open - Opened by lxb0425 3 months ago
Labels: question

#2029 - merge_vad 后，推理遇到的两个问题

Issue - State: closed - Opened by Joy-word 3 months ago - 4 comments
Labels: bug

#2029 - merge_vad 后，推理遇到的两个问题

Issue - State: closed - Opened by Joy-word 3 months ago - 5 comments
Labels: bug

#2028 - GPU版本读取speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx模型报错

Issue - State: closed - Opened by wddan 3 months ago - 1 comment
Labels: question

#2028 - GPU版本读取speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx模型报错

Issue - State: closed - Opened by wddan 3 months ago - 1 comment
Labels: question

#2027 - SenseVoiceSmall没有带时间戳

Issue - State: open - Opened by SpringSan 3 months ago
Labels: bug

#2027 - SenseVoiceSmall没有带时间戳

Issue - State: closed - Opened by SpringSan 3 months ago - 1 comment
Labels: bug

#2026 - 这几个模型名到底都能填写什么？

Issue - State: open - Opened by leavegee 3 months ago
Labels: question

#2026 - 这几个模型名到底都能填写什么？

Issue - State: open - Opened by leavegee 3 months ago - 1 comment
Labels: question

#2025 - Llm

Pull Request - State: closed - Opened by LauraGPT 3 months ago

#2024 - fix start timestamp in sentence_info

Pull Request - State: closed - Opened by lingji-yidong 3 months ago

#2024 - fix start timestamp in sentence_info

Pull Request - State: closed - Opened by lingji-yidong 3 months ago

#2023 - wrong submit. sorry for that.

Issue - State: open - Opened by laishuzhong 3 months ago
Labels: bug

#2023 - wrong submit. sorry for that.

Issue - State: closed - Opened by laishuzhong 3 months ago
Labels: bug

#2022 - donate list

Pull Request - State: closed - Opened by bltcn 3 months ago

#2022 - donate list

Pull Request - State: closed - Opened by bltcn 3 months ago

#2021 - GPU版本：[W shape_analysis.cpp:841] failed PropagateTensorShapeOnNode with schema

Issue - State: open - Opened by zhanglv0209 3 months ago - 1 comment
Labels: documentation

#2021 - GPU版本：[W shape_analysis.cpp:841] failed PropagateTensorShapeOnNode with schema

Issue - State: closed - Opened by zhanglv0209 3 months ago - 2 comments
Labels: documentation

#2020 - label_smoothing_loss target None

Issue - State: closed - Opened by kli017 3 months ago
Labels: bug

#2019 - docker gpu1.1长文件时间戳偏移很大

Issue - State: open - Opened by dfengpo 3 months ago
Labels: bug

#2019 - docker gpu1.1长文件时间戳偏移很大

Issue - State: open - Opened by dfengpo 3 months ago - 3 comments
Labels: bug

#2018 - parformer大规模数据集预训练cpu内存持续增加的问题

Issue - State: open - Opened by chenpaopao 3 months ago
Labels: question

#2018 - parformer大规模数据集预训练cpu内存持续增加的问题

Issue - State: open - Opened by chenpaopao 3 months ago
Labels: question

#2017 - 无法理解传入的参数，使用ASR

Issue - State: open - Opened by deadash 3 months ago - 2 comments
Labels: question

#2017 - 无法理解传入的参数，使用ASR

Issue - State: open - Opened by deadash 3 months ago - 2 comments
Labels: question

#2016 - 微调sensevoice模型Update best acc: 0.0000

Issue - State: open - Opened by xiulianzw 3 months ago - 3 comments
Labels: question

#2016 - 微调sensevoice模型Update best acc: 0.0000

Issue - State: open - Opened by xiulianzw 3 months ago
Labels: question