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.
目前的代码（master head）onnx 在 windows 下无法编译（Onnx runtime 1.15.1），希望支持一下，自己通过修改代码解决了一下，因为处理的比较乱，没好意思提交 PR： ### 支持 windows 修改： #### 1. Onnx session 构造函数签名宽字符问题. 例如： ```cpp std::make_unique(env_, punc_model.c_str(), session_options); ``` 修改一下： ```cpp auto path = StrToWstr(punc_model); m_session...
linux:Ubuntu 20.04.4 python=3.8.18 torch=2.0.1 funasr=0.8.2 modelscope=1.9.3 在训练模型的stage1，没有生成cmvn.json和am.mvn文件是什么原因啊，怎么排查这个错误
使用标点符号添加模型进行处理， 书名号中内容被添加标点。 ` inference_pipline = pipeline( task=Tasks.punctuation, model='damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch', model_revision="v1.1.7") tmp_str = "《内容测试》内容测试内容司内容" inference_pipline(text_in=tmp_str) ` 输出结果： 《内容测试。》内容测试内容司内容 期望： 书名号中内容不要进行添加
参考文档： https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary 版本： `funasr 0.8.6` 代码： `from modelscope.pipelines import pipeline from modelscope.utils.constant import Tasks audio_in = 'wangfang.wav' output_dir = "./results" inference_pipeline = pipeline( task=Tasks.auto_speech_recognition, model='damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn', model_revision='v0.0.2', vad_model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch', punc_model='damo/punc_ct-transformer_cn-en-common-vocab471067-large', output_dir=output_dir, )...
linux:Ubuntu 20.04.4 python=3.8.18 torch=2.0.1 funasr=0.8.2 modelscope=1.9.3 200小时的数据，lr=0.001，epoch=180，训练e_branchformer，最终的效果在验证集上很差是什么原因啊 
RT 例如这样： asr_pipeline = pipeline( task=Tasks.auto_speech_recognition, model="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404", vad_model='damo/speech_fsmn_vad_zh-cn-16k-common-pytorch', punc_model='damo/punc_ct-transformer_cn-en-common-vocab471067-large', ngpu=1, batch_size=5000） param_dict = dict() param_dict['hotword'] = "短视频" param_dict['clas_scale'] = 1.50 asr_pipeline(_samples, param_dict) 
我的应用场景是Windows，想把客户端集成到其它项目中，昨天Cmake了下cpp-client，在vs上编译太多错误了，想咨询下关于Windows平台下的客户端会不会出单独sdk，或者有没有什么办法可以解决我这种问题呢？
After itn, some words may transform to other representation, which make new representation can't search in the timestamp list. We should make a calibration of timestamp list after itn. old...
After I change the batch_size to 15000 for training, I have a size mismatch problem in the decoding phase, please answer. Below are the specific error codes: 2023-12-04 09:45:29,392 -...
OS: Linux 最新的镜像 registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.2 模型： download_model_dir="/workspace/models" model_dir="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404-onnx" online_model_dir="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online-onnx" vad_dir="damo/speech_fsmn_vad_zh-cn-16k-common-onnx" itn_dir="thuduj12/fst_itn_zh" decoder_thread_num=32 io_thread_num=8 port=10031 certfile=0 # "../../../ssl_key/server.crt" keyfile=0 # "../../../ssl_key/server.key" punc_dir="damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727-onnx" 前端连接服务导致报错： terminate called after throwing an instance of 'nlohmann::json_abi_v3_11_2::detail::parse_error' what():...
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.