FunASR
FunASR copied to clipboard
modelscope
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
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...
Hi, Thanks for the wonderful project! I'm wondering whether there is any plan for the rust implementations. #### What is your question? Is there any plan to have a rust...
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） #1768 的需求一致，但是目前仍然不支持加载 #### What is your question? 目前电信的ASR模型对方言的支持效果很好，但是不知道如何改写其config让其支持FunASR，模型如下 https://github.com/Tele-AI/TeleSpeech-ASR/tree/bc93f1b5835a593df48e4a4485d5b8d1cfe2afbb https://www.modelscope.cn/models/TeleAI/TeleSpeech-ASR1.0 #### What have you tried?...
有2个问题， 1.官方提供的调用方式是websocket和grpc，这个grpc是一直有维护吗 2.官网的接口文档里有提供grpc的接口文档，但是在文档里寻找不到部署的步骤，我看/workspace/FunASR/runtime/grpc里的Readme.md文档里有grpc的编译方式，出现了问题有文档吗 - OS : Linux - Docker version : 24.0.7 - image version : funasr-runtime-sdk-online-cpu-0.1.10
 ![Uploading 1720062605218.png…]()
不管是从modelscope.pipelines还是从funasr.AutoModel加载模型，后面推理的时候都会报错Cannot find available config to build preprocessor at mode inference, current config
使用/runtime/python/websocket下的代码进行测试，mode为2pass，在使用过程中发现支持热词的离线模型在总体识别效果上弱于非热词模型，热词模型更容易出现“嗯”“啊”之类的语气词，非热词模型会纠正掉，请问热词模型是否会降低识别效果？如有，应该如何解决？ #### asr_model_online: - speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online #### vad_model: - speech_fsmn_vad_zh-cn-16k-common-pytorch #### punc_model: - punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727 #### 离线模型： - speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch #### 热词模型: - speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch - speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404 #### What's your environment? - OS (e.g.,...
Is it possible to finetube the punctuation model independently? What is the format of the labels of the training data?
``` 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", # spk_model="cam++", )...
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...
Metadata
Owner
Metadata
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.