issues
search
modelscope
/
FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
https://www.funasr.com
Other
6.99k
stars
744
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
IndexError: index 3 is out of bounds for dimension 1 with size 2
#2211
JonneryR
opened
2 days ago
1
Intel MKL function load error: mkl_vml_kernel_sLn_ttab.
#2210
1749352011
opened
3 days ago
0
Add bounds check for postprocess_utils.py abbr_dispose()
#2209
BitSteve
closed
3 days ago
0
请问Paraformer-V2的代码会开源吗？
#2208
NiniAndy
opened
4 days ago
0
PCM录音文件读取似乎有问题
#2207
wjm030612
opened
5 days ago
1
paraformer_large_offline triton运行bug 修复
#2206
yijinsheng
closed
5 days ago
1
paraformer_large_offline triton运行bug 修复
#2205
yijinsheng
closed
6 days ago
0
cpu离线版本，客户端建立websocket请求，串行推送多个48k的语音wav，语音转写服务会重启，而且概率很高，log.txt也没见具体报错原因。生成的dmp（每次5g左右）文件会导致docker容器不断的变大。
#2204
janchou92
opened
1 week ago
2
FunASR 语音识别中的回声问题？
#2203
JACKYLUO1991
opened
1 week ago
0
vad FSMN语音端点检测-中文-通用-16k 内存泄漏问题
#2202
tonyzzzzz
closed
1 week ago
0
GPU版找不到文件model_blade.torchscript
#2201
Jotree2012
opened
1 week ago
2
使用iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch模型，运行offline_gpu服务报错
#2200
gzqqqqqq
opened
1 week ago
2
使用damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404模型，运行offline_gpu服务报错
#2199
gzqqqqqq
opened
1 week ago
0
funasr有没有类似于faster_whisper的whisperModel().transcribe的功能，可以获取segments?
#2198
liuchangzong
opened
1 week ago
1
vad 模式切割的音频在转录后会自己删除吗
#2197
lesrose
opened
1 week ago
0
docker服务端发送文本内容过长，超出缓冲区，导致消息发送失败
#2196
psk-github
opened
1 week ago
0
FunASR开源项目体验demo中路径runtime/python/websocket/funasr_wss_server.py中没有timestamp时间戳，在线体验中的时间戳从何而来？
#2195
mrblacklee
closed
1 week ago
1
标点重建模型在推理增加英文标点时将单词拆开
#2194
bigcash
opened
1 week ago
0
怎么使用流式的fsmn-kws
#2193
hajkeoadf
opened
1 week ago
0
在language identification中funasr 的问题
#2192
panxin801
opened
1 week ago
0
中文实时语音听写服务是否支持语音唤醒模型
#2191
hajkeoadf
closed
1 week ago
1
第一次执行Quick Start中的命令时被意外中断，之后一直报modelscope - ERROR - 400 Client Error: Bad Request，似乎无法下载任何模型
#2190
HexJay
closed
1 week ago
1
RuntimeError: "round_cuda" not implemented for 'Long'
#2189
lukeewin
closed
1 week ago
1
安装了最新的1.1.6版本，还是报错choose a window size 400 that is [2, 160]
#2188
hjj-lmx
closed
1 week ago
1
安装了最新的1.1.6版本，还是报错choose a window size 400 that is [2, 160]
#2187
hjj-lmx
closed
1 week ago
0
Fix audio format 2.0
#2186
Djraemon
closed
2 weeks ago
0
Paraformer-en模型在推理时报错，spm index超出范围
#2185
MrSupW
closed
1 week ago
1
能说一下docker里面/etc/docker/daemon的原理和使用方法吗
#2184
tiandiweizun
opened
2 weeks ago
0
springboot集成modelscope模型
#2183
zhangzhaogit
opened
2 weeks ago
1
在Window10家庭版安装funasr报错Failed to build aliyun-python-sdk-core，使用pip install源码安装都不行
#2182
jhchhz
closed
1 week ago
2
使用微调之后的模型音频识别为空
#2181
fjt12138
opened
2 weeks ago
1
C++ Websocket多线程卡住
#2180
monsterlyg
closed
2 weeks ago
2
为什么我的识别结果格式和平台在线的不一样，求好心人告知
#2179
ordinary-lv
closed
1 week ago
1
seaco语音模型微调报错：'NoneType' object has no attribute 'contiguous'
#2178
smengfei
closed
1 week ago
5
perf(models/FsmnVADStreaming): optimize GetFrameState() and PopDataToOutputBuf()
#2177
truc0
closed
2 weeks ago
0
seaco语音模型微调报错：'NoneType' object has no attribute 'contiguous'
#2176
smengfei
closed
3 weeks ago
0
Enhanced Evaluation Script with Argument Validation, Structured Error Handling, and Detailed Token-Level Reporting in run_evaluate.py
#2175
vignesh1507
closed
2 weeks ago
0
optimize ComputeDecibel in fsmn-vad model by using numpy
#2174
hongfanmeng
closed
3 weeks ago
0
部署FunASR离线文件转写服务GPU版本时出错
#2173
17806233962
closed
3 weeks ago
0
长语音识别的问题
#2172
jlljill
opened
3 weeks ago
0
求助 我们用funasr接受麦克风音频，用mediapipe判断嘴唇与说话频率问题在于如果嘴张开动没有说话，旁边的人说话，系统会认为是检测(mediapipe识别到的人脸)到的人在说话
#2171
Redhair957
closed
1 week ago
1
There is no key "file_path_metas" in Qwen-Audio/configuration.json
#2170
JiajunDou
opened
3 weeks ago
0
fsmn-vad 模型似乎有 CPU 性能问题
#2168
hongfanmeng
closed
3 weeks ago
5
Add Contribution.md to the main branch.
#2167
vignesh1507
closed
3 weeks ago
0
能否微调成一个分类任务，target为每条语音的分类标签
#2166
chaunceyliu30
closed
1 week ago
1
按照seacoparaformer中finetune.sh微调时报错，是不是需要修改["source", "target"]呢？改成热词版的数据格式呢？
#2165
YouTwoMeToo
closed
3 weeks ago
1
docker镜像funasr-runtime-sdk-online-cpu-0.1.11，每次链接建立都造成内存增加，断开后内存不下降
#2164
EAGLE50
closed
2 weeks ago
3
请问微调后的模型，如何计算字错率？
#2163
lukeewin
closed
3 weeks ago
1
Paraformer语音识别-中文-通用-16k-离线-large-长音频版，微调量化导出后的模型文件替换docker中的模型文件后的效果与本地验证不一样
#2162
chiyinbao
opened
3 weeks ago
1
C++服务端WebSocket添加鉴权功能
#2161
cuiyuanzhe
opened
3 weeks ago
5
Next