FunASR

FunASR copied to clipboard

## 🐛 Bug 客户端 服务端 ### To Reproduce 启动服务端正常，PYTHON客户端提交后，服务端显示了个 new user connected，就一直卡着没有反应 是用源码安装的 ### Environment - OS : WIN10 - FunASR Version : 1.27 - ModelScope Version (e.g., 1.11.0): -...

heiheiheibj

from funasr import AutoModel # paraformer-zh is a multi-functional asr model # use vad, punc, spk or not as you need model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc", disable_update=False # spk_model="cam++", )...

PengChaoJay

onnx模型的推理速度更慢是为什么呢？

3

在cpu上尝试进行onnx模型的导出和推理测试，在示例音频example/en.wav上进行推理测试 torch： onnx-cpu： 这里是我的硬件信息：

oak-JHCheng

whisper的model.py文件里面forward函数只有一个pass

moro0v0

OOM when setting batchtype='token' and size mismatch when setting batchtype='example'

2

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 ### To Reproduce Steps to reproduce the behavior (**always include the command...

OedonLestrange42

CPP runtime 可以运行seaco模型嘛？

boji123

/workspace/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx is not registered

4

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 ### Before asking: 1. search the issues. 2. search the...

dong6255

https://www.xiangongyun.com/image/detail/4c2e8222-3175-4f07-8378-0d8d6ca99ba4?r=WZFDHU

qq36545

FunASR提供了便捷的脚本和教程，支持预训练好的模型的推理与微调？

1

## 微调 语音识别微调如何做，微调的程序在那里，谢谢

yourengod

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 识别PCM音频，报错"Failed to load audio" ### To Reproduce 识别pcm扩展名（16k 1c 16bit）音频，报"Failed to load...

weilikai