FunASR icon indicating copy to clipboard operation
FunASR copied to clipboard

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Results 555 FunASR issues
Sort by recently updated
recently updated
newest added
trafficstars

“FunASR/funasr/runtime/python/onnxruntime”是一个不存在的路径,在执行“cd FunASR”之后,如果用户再执行“cd funasr/runtime/python/onnxruntime”会出现错误。 虽然funasr_onnx用到了onnxruntime,但实际上它并未用到onnx库。(仅安装funasr_onnx,不安装完整的funasr Python包,是不需要import onnx的)但onnx出现在了install_requires中。 jieba库未出现在install_requires中,但 FunASR/runtime/python/onnxruntime/funasr_onnx/utils/utils.py 使用到它了。 "FunASR/funasr/runtime/python/onnxruntime" is an invalid path. After executing "cd FunASR", if the user executes "cd funasr/runtime/python/onnxruntime", an error will occur. Although funasr_onnx...

## 🐛 Bug ### To Reproduce Steps to reproduce the behavior (**always include the command you ran**): 1. Run cmd `./funasr-http-server --vad-dir ~/.cache/modelscope/hub/models/iic/speech_fsmn_vad_zh-cn-16k-common-pytorch --model-dir ~/.cache/modelscope/hub/models/iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --itn-dir '' --lm-dir '' --hotword...

bug

### Environment - OS (e.g., Linux): Ubuntu Server 22.04 - FunASR Version (e.g., 1.0.0): 1.1.12 - ModelScope Version (e.g., 1.11.0): 1.19.2 - PyTorch Version (e.g., 2.0.0): 2.5 - How you...

bug

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 ``` $ openssl s_client -connect www.funasr.com:443 -servername www.funasr.com -verify_return_error Connecting to 198.18.19.251...

bug

我测试了导出的量化INT8的SenseVoiceSmall产生的onnx模型直接拿cpu和gpu去预测一个语音模型,观察到语音模型在使用cpu第一次只要1s多第二次只要0.1s。然后使用gpu反而更忙了第一次20s,第二次1s。这是什么问题

question

With demo code, I got error like "can not get `timestamp`": ```python from funasr import AutoModel from funasr.utils.postprocess_utils import rich_transcription_postprocess model_dir = "iic/SenseVoiceSmall" model = AutoModel( model=model_dir, vad_model="fsmn-vad", vad_kwargs={"max_single_segment_time": 30000},...

question

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...

bug

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 在gpu offline的启动命令中 nohup bash run_server.sh \ --download-model-dir /workspace/models \ --model-dir...

question